BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Ming Zhou

Ming Zhou appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computation and LanguageMachine LearningArtificial IntelligenceComputer Visionastro-ph.HEeess.ASInformation Retrievalmath.NAMultiagent SystemsNumerical Analysisphysics.opticsSoundastro-ph.GAProgramming Languagesquant-phRoboticsComputer Science and Game Theorycond-mat.mes-halleess.IVMultimediaNeural and Evolutionary ComputingOther Quantitative Biologyphysics.app-phphysics.comp-phphysics.data-anphysics.ins-detphysics.soc-phSoftware Engineering

Catalog footprint

What is connected

62works
28topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

62 published item(s)

preprint2026arXiv

All-Optical Deep Learning with Quantum Nonlinearity

The rapid scaling of deep neural networks comes at the cost of unsustainable power consumption. While optical neural networks offer an alternative, their capabilities remain constrained by the lack of efficient optical nonlinearities. To address this, we propose an all-optical deep learning architecture by embedding quantum emitters in inverse-designed nanophotonic structures. Due to their saturability, quantum emitters exhibit exceptionally strong nonlinearity compared with conventional materials. Using physics-aware training, we demonstrate that the proposed architecture can solve complex tasks, including nonlinear classification and reinforcement learning, which have not been realized in all-optical neural networks. To enable fair comparison across different platforms, we introduce a framework that quantitatively links nonlinearity to a network's expressive power. Analysis shows that our quantum activation, operating below nW/μm^2 intensity, reduces the power budget by seven orders of magnitude. System-level estimates show that the optical power required for large language models scales sublinearly with model size, enabling watt-level operation. Our results indicate that quantum nanophotonics provides a route toward sustainable AI inference.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos

Monocular video human mesh recovery is essential for digital humans, avatar animation, and embodied simulation, where both temporal stability and expressive whole-body motion are required. Existing video HMR methods produce coherent body motion but often overlook detailed hand articulation, while image-based whole-body methods recover SMPL-X meshes independently per frame, often leading to jittery and inaccurate hand motion. We present a temporally coherent whole-body HMR framework for challenging in-the-wild monocular videos. Our model unifies body context and part-specific hand observations through residual body-hand fusion, enabling stable body motion and detailed hand recovery within a single temporal architecture. We further introduce close-up-aware augmentation to improve robustness under upper-body framing. Experiments on whole-body and body-only benchmarks demonstrate improved hand reconstruction and competitive body accuracy. Our method also produces temporally stable and 2D-consistent SMPL-X motion in challenging real-world videos.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization

Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements in control precision, most RL optimizers remain task-specific, which reduces VLA models from generalist controllers to policies that overfit to a narrow set of tasks. In this study, we conduct an in-depth analysis of this phenomenon and highlight the importance of cross-task feature representations for improving the generalizability of VLA models. Motivated by this finding, we introduce DyGRO-VLA, a two-stage optimization framework that 1) effectively captures cross-task latent representations based on information-theoretic principles, and 2) dynamically refines policy optimization via a mixture-of-RL-residuals. DyGRO-VLA enables the RL optimizer to exploit task-relevant latent information while strategically mitigating adverse interference on the learned representations throughout the optimization process. We evaluate our approach on LIBERO, RoboTwin2 benchmarks, and further validate it on real world, demonstrating consistent improvements over strong baselines under multi-task training and distribution shift.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Toward genuine efficiency and cluster robustness of preconditioned CG-like eigensolvers

The performance of eigenvalue problem solvers (eigensolvers) depends on various factors such as preconditioning and eigenvalue distribution. Developing stable and rapidly converging vectorwise eigensolvers is a crucial step in improving the overall efficiency of their blockwise implementations. The present paper is concerned with the locally optimal block preconditioned conjugate gradient (LOBPCG) method for Hermitian eigenvalue problems, and motivated by two recently proposed alternatives for its single-vector version LOPCG. A common basis of these eigensolvers is the well-known CG method for linear systems. However, the optimality of CG search directions cannot perfectly be transferred to CG-like eigensolvers. In particular, while computing clustered eigenvalues, LOPCG and its alternatives suffer from frequent delays, leading to a staircase-shaped convergence behavior which cannot be explained by the existing estimates. Keeping this in mind, we construct a class of cluster robust vector iterations where LOPCG is replaced by asymptotically equivalent two-term recurrences and the search directions are timely corrected by selecting a far previous iterate as augmentation. The new approach significantly reduces the number of required steps and the total computational time.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A density peaks clustering algorithm with sparse search and K-d tree

Density peaks clustering has become a nova of clustering algorithm because of its simplicity and practicality. However, there is one main drawback: it is time-consuming due to its high computational complexity. Herein, a density peaks clustering algorithm with sparse search and K-d tree is developed to solve this problem. Firstly, a sparse distance matrix is calculated by using K-d tree to replace the original full rank distance matrix, so as to accelerate the calculation of local density. Secondly, a sparse search strategy is proposed to accelerate the computation of relative-separation with the intersection between the set of $k$ nearest neighbors and the set consisting of the data points with larger local density for any data point. Furthermore, a second-order difference method for decision values is adopted to determine the cluster centers adaptively. Finally, experiments are carried out on datasets with different distribution characteristics, by comparing with other six state-of-the-art clustering algorithms. It is proved that the algorithm can effectively reduce the computational complexity of the original DPC from $O(n^2K)$ to $O(n(n^{1-1/K}+k))$. Especially for larger datasets, the efficiency is elevated more remarkably. Moreover, the clustering accuracy is also improved to a certain extent. Therefore, it can be concluded that the overall performance of the newly proposed algorithm is excellent.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adversarial Fine-tune with Dynamically Regulated Adversary

Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks. However, such improvement in model robustness often leads to a significant sacrifice of standard performance on clean images. In many real-world applications such as health diagnosis and autonomous surgical robotics, the standard performance is more valued over model robustness against such extremely malicious attacks. This leads to the question: To what extent we can boost model robustness without sacrificing standard performance? This work tackles this problem and proposes a simple yet effective transfer learning-based adversarial training strategy that disentangles the negative effects of adversarial samples on model's standard performance. In addition, we introduce a training-friendly adversarial attack algorithm, which facilitates the boost of adversarial robustness without introducing significant training complexity. Extensive experimentation indicates that the proposed method outperforms previous adversarial training algorithms towards the target: to improve model robustness while preserving model's standard performance on clean data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

Standard automatic metrics, e.g. BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discourse phenomena that cause context-agnostic translations. This paper introduces a novel automatic metric BlonDe to widen the scope of automatic MT evaluation from sentence to document level. BlonDe takes discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans. We conduct extensive comparisons on a newly constructed dataset BWB. The experimental results show that BlonDe possesses better selectivity and interpretability at the document-level, and is more sensitive to document-level nuances. In a large-scale human study, BlonDe also achieves significantly higher Pearson's r correlation with human judgments compared to previous metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Convergence analysis of a block preconditioned steepest descent eigensolver with implicit deflation

Gradient-type iterative methods for solving Hermitian eigenvalue problems can be accelerated by using preconditioning and deflation techniques. A preconditioned steepest descent iteration with implicit deflation (PSD-id) is one of such methods. The convergence behavior of the PSD-id is recently investigated based on the pioneering work of Samokish on the preconditioned steepest descent method (PSD). The resulting non-asymptotic estimates indicate a superlinear convergence of the PSD-id under strong assumptions on the initial guess. The present paper utilizes an alternative convergence analysis of the PSD by Neymeyr under much weaker assumptions. We embed Neymeyr's approach into the analysis of the PSD-id using a restricted formulation of the PSD-id. More importantly, we extend the new convergence analysis of the PSD-id to a practically preferred block version of the PSD-id, or BPSD-id, and show the cluster robustness of the BPSD-id. Numerical examples are provided to validate the theoretical estimates.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Convergence rates of individual Ritz values in block preconditioned gradient-type eigensolvers

Many popular eigensolvers for large and sparse Hermitian matrices or matrix pairs can be interpreted as accelerated block preconditioned gradient (BPG) iterations in order to analyze their convergence behavior by composing known estimates. An important feature of BPG is the cluster robustness, i.e., reasonable performance for computing clustered eigenvalues is ensured by a sufficiently large block size. This feature can easily be explained for exact-inverse (exact shift-inverse) preconditioning by adapting classical estimates on nonpreconditioned eigensolvers, whereas the existing results for more general preconditioning are still improvable. We expect to extend certain sharp estimates for the corresponding vector iterations to BPG where proper bounds of convergence rates of individual Ritz values are to be derived. Such an extension has been achieved for BPG with fixed step sizes in [Math. Comp. 88 (2019), 2737--2765]. The present paper deals with the more practical case that the step sizes are implicitly optimized by the Rayleigh-Ritz method. Our new estimates improve some previous ones in view of concise and more flexible bounds.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient Policy Space Response Oracles

Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game evaluation via simulations, and (2) the exploration inefficiency due to finding the best response against a fixed meta-strategy at every epoch. In this work, we propose Efficient PSRO (EPSRO) that largely improves the efficiency of the above two steps. Central to our development is the newly-introduced subroutine of no-regret optimization on the unrestricted-restricted (URR) game. By solving URR at each epoch, one can evaluate the current game and compute the best response in one forward pass without the need for meta-game simulations. Theoretically, we prove that the solution procedures of EPSRO offer a monotonic improvement on the exploitability, which none of existing PSRO methods possess. Furthermore, we prove that the no-regret optimization has a regret bound of $\mathcal{O}(\sqrt{T\log{[(k^2+k)/2]}})$, where $k$ is the size of restricted policy set. Most importantly, a desirable property of EPSRO is that it is parallelizable, this allows for highly efficient exploration in the policy space that induces behavioral diversity. We test EPSRO on three classes of games, and report a 50x speedup in wall-time and 10x data efficiency while maintaining similar exploitability as existing PSRO methods on Kuhn and Leduc Poker games.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generative Adversarial Exploration for Reinforcement Learning

Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel. Most previous work focuses on designing heuristic rules or distance metrics to check whether a state is novel without considering such a discrimination process that can be learned. In this paper, we propose a novel method called generative adversarial exploration (GAEX) to encourage exploration in RL via introducing an intrinsic reward output from a generative adversarial network, where the generator provides fake samples of states that help discriminator identify those less frequently visited states. Thus the agent is encouraged to visit those states which the discriminator is less confident to judge as visited. GAEX is easy to implement and of high training efficiency. In our experiments, we apply GAEX into DQN and the DQN-GAEX algorithm achieves convincing performance on challenging exploration problems, including the game Venture, Montezuma's Revenge and Super Mario Bros, without further fine-tuning on complicate learning algorithms. To our knowledge, this is the first work to employ GAN in RL exploration problems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improving Task Generalization via Unified Schema Prompt

Task generalization has been a long standing challenge in Natural Language Processing (NLP). Recent research attempts to improve the task generalization ability of pre-trained language models by mapping NLP tasks into human-readable prompted forms. However, these approaches require laborious and inflexible manual collection of prompts, and different prompts on the same downstream task may receive unstable performance. We propose Unified Schema Prompt, a flexible and extensible prompting method, which automatically customizes the learnable prompts for each task according to the task input schema. It models the shared knowledge between tasks, while keeping the characteristics of different task schema, and thus enhances task generalization ability. The schema prompt takes the explicit data structure of each task to formulate prompts so that little human effort is involved. To test the task generalization ability of schema prompt at scale, we conduct schema prompt-based multitask pre-training on a wide variety of general NLP tasks. The framework achieves strong zero-shot and few-shot generalization performance on 16 unseen downstream tasks from 8 task types (e.g., QA, NLI, etc). Furthermore, comprehensive analyses demonstrate the effectiveness of each component in the schema prompt, its flexibility in task compositionality, and its ability to improve performance under a full-data fine-tuning setting.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry

Leveraging line features can help to improve the localization accuracy of point-based monocular Visual-Inertial Odometry (VIO) system, as lines provide additional constraints. Moreover, in an artificial environment, some straight lines are parallel to each other. In this paper, we designed a VIO system based on points and straight lines, which divides straight lines into structural straight lines (that is, straight lines parallel to each other) and non-structural straight lines. In addition, unlike the orthogonal representation using four parameters to represent the 3D straight line, we only used two parameters to minimize the representation of the structural straight line and the non-structural straight line. Furthermore, we designed a straight line matching strategy based on sampling points to improve the efficiency and success rate of straight line matching. The effectiveness of our method is verified on both public datasets of EuRoc and TUM VI benchmark and compared with other state-of-the-art algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low sample complexity during the whole learning process, we propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO). In AORPO, each agent builds its multi-agent environment model, consisting of a dynamics model and multiple opponent models, and trains its policy with the adaptive opponent-wise rollout. We further prove the theoretic convergence of AORPO under reasonable assumptions. Empirical experiments on competitive and cooperative tasks demonstrate that AORPO can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centric Reasoning and Pre-training framework (CARP). CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering. We also propose a novel chain-centric pre-training method, to enhance the pre-trained model in identifying the cross-modality reasoning process and alleviating the data sparsity problem. This method constructs the large-scale reasoning corpus by synthesizing pseudo heterogeneous reasoning paths from Wikipedia and generating corresponding questions. We evaluate our system on OTT-QA, a large-scale table-and-text open-domain question answering benchmark, and our system achieves the state-of-the-art performance. Further analyses illustrate that the explicit hybrid chain offers substantial performance improvement and interpretablity of the intermediate reasoning process, and the chain-centric pre-training boosts the performance on the chain extraction.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

Pre-trained models for programming languages have recently demonstrated great success on code intelligence. To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models. However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference. In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language. The model utilizes mask attention matrices with prefix adapters to control the behavior of the model and leverages cross-modal contents like AST and code comment to enhance code representation. To encode AST that is represented as a tree in parallel, we propose a one-to-one mapping method to transform AST in a sequence structure that retains all structural information from the tree. Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task. We evaluate UniXcoder on five code-related tasks over nine datasets. To further evaluate the performance of code fragment representation, we also construct a dataset for a new task, called zero-shot code-to-code search. Results show that our model achieves state-of-the-art performance on most tasks and analysis reveals that comment and AST can both enhance UniXcoder.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts

We study question answering over a dynamic textual environment. Although neural network models achieve impressive accuracy via learning from input-output examples, they rarely leverage various types of knowledge and are generally not interpretable. In this work, we propose a graph-based approach, where a heterogeneous graph is automatically built with factual knowledge of the context, temporal knowledge of the past states, and logical knowledge that combines human-curated knowledge bases and rule bases. We develop a graph neural network over the constructed graph, and train the model in an end-to-end manner. Experimental results on a benchmark dataset show that the injection of various types of knowledge improves a strong neural network baseline. An additional benefit of our approach is that the graph itself naturally serves as a rational behind the decision making.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

CodeBERT: A Pre-Trained Model for Programming and Natural Languages

We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, where the former provides input tokens for model training while the latter helps to learn better generators. We evaluate CodeBERT on two NL-PL applications by fine-tuning model parameters. Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks. Furthermore, to investigate what type of knowledge is learned in CodeBERT, we construct a dataset for NL-PL probing, and evaluate in a zero-shot setting where parameters of pre-trained models are fixed. Results show that CodeBERT performs better than previous pre-trained models on NL-PL probing.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Curriculum Pre-training for End-to-End Speech Translation

End-to-end speech translation poses a heavy burden on the encoder, because it has to transcribe, understand, and learn cross-lingual semantics simultaneously. To obtain a powerful encoder, traditional methods pre-train it on ASR data to capture speech features. However, we argue that pre-training the encoder only through simple speech recognition is not enough and high-level linguistic knowledge should be considered. Inspired by this, we propose a curriculum pre-training method that includes an elementary course for transcription learning and two advanced courses for understanding the utterance and mapping words in two languages. The difficulty of these courses is gradually increasing. Experiments show that our curriculum pre-training method leads to significant improvements on En-De and En-Fr speech translation benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension

Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragraphs, sentences, and tokens. We utilize graph attention networks to obtain different levels of representations so that they can be learned simultaneously. The long and short answers can be extracted from paragraph-level representation and token-level representation, respectively. In this way, we can model the dependencies between the two-grained answers to provide evidence for each other. We jointly train the two sub-tasks, and our experiments show that our approach significantly outperforms previous systems at both long and short answer criteria.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs. Existing works usually ignore the context that is not explicitly provided, resulting in a context-independent semantic representation that struggles to support the generation. To address this, we propose an approach that automatically finds evidence for an event from a large text corpus, and leverages the evidence to guide the generation of inferential texts. Our approach works in an encoder-decoder manner and is equipped with a Vector Quantised-Variational Autoencoder, where the encoder outputs representations from a distribution over discrete variables. Such discrete representations enable automatically selecting relevant evidence, which not only facilitates evidence-aware generation, but also provides a natural way to uncover rationales behind the generation. Our approach provides state-of-the-art performance on both Event2Mind and ATOMIC datasets. More importantly, we find that with discrete representations, our model selectively uses evidence to generate different inferential texts.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Inferential Text Generation with Multiple Knowledge Sources and Meta-Learning

We study the problem of generating inferential texts of events for a variety of commonsense like \textit{if-else} relations. Existing approaches typically use limited evidence from training examples and learn for each relation individually. In this work, we use multiple knowledge sources as fuels for the model. Existing commonsense knowledge bases like ConceptNet are dominated by taxonomic knowledge (e.g., \textit{isA} and \textit{relatedTo} relations), having a limited number of inferential knowledge. We use not only structured commonsense knowledge bases, but also natural language snippets from search-engine results. These sources are incorporated into a generative base model via key-value memory network. In addition, we introduce a meta-learning based multi-task learning algorithm. For each targeted commonsense relation, we regard the learning of examples from other relations as the meta-training process, and the evaluation on examples from the targeted relation as the meta-test process. We conduct experiments on Event2Mind and ATOMIC datasets. Results show that both the integration of multiple knowledge sources and the use of the meta-learning algorithm improve the performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

LayoutLM: Pre-training of Text and Layout for Document Image Understanding

Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the \textbf{LayoutLM} to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage image features to incorporate words' visual information into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pre-training. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42). The code and pre-trained LayoutLM models are publicly available at \url{https://aka.ms/layoutlm}.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning to Summarize Passages: Mining Passage-Summary Pairs from Wikipedia Revision Histories

In this paper, we propose a method for automatically constructing a passage-to-summary dataset by mining the Wikipedia page revision histories. In particular, the method mines the main body passages and the introduction sentences which are added to the pages simultaneously. The constructed dataset contains more than one hundred thousand passage-summary pairs. The quality analysis shows that it is promising that the dataset can be used as a training and validation set for passage summarization. We validate and analyze the performance of various summarization systems on the proposed dataset. The dataset will be available online at https://res.qyzhou.me.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network

Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this work, we propose LogicalFactChecker, a neural network approach capable of leveraging logical operations for fact checking. It achieves the state-of-the-art performance on TABFACT, a large-scale, benchmark dataset built for verifying a textual statement with semi-structured tables. This is achieved by a graph module network built upon the Transformer-based architecture. With a textual statement and a table as the input, LogicalFactChecker automatically derives a program (a.k.a. logical form) of the statement in a semantic parsing manner. A heterogeneous graph is then constructed to capture not only the structures of the table and the program, but also the connections between inputs with different modalities. Such a graph reveals the related contexts of each word in the statement, the table and the program. The graph is used to obtain graph-enhanced contextual representations of words in Transformer-based architecture. After that, a program-driven module network is further introduced to exploit the hierarchical structure of the program, where semantic compositionality is dynamically modeled along the program structure with a set of function-specific modules. Ablation experiments suggest that both the heterogeneous graph and the module network are important to obtain strong results.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Low Latency End-to-End Streaming Speech Recognition with a Scout Network

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition accuracy when applying a fixed-length look-ahead window in each encoder layer. In this paper, we propose a novel low-latency streaming approach for Transformer models, which consists of a scout network and a recognition network. The scout network detects the whole word boundary without seeing any future frames, while the recognition network predicts the next subword by utilizing the information from all the frames before the predicted boundary. Our model achieves the best performance (2.7/6.4 WER) with only 639 ms latency on the test-clean and test-other data sets of Librispeech.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and online serving in real-life applications due to latency and capacity constraints. In this work, we present a simple and effective approach to compress large Transformer (Vaswani et al., 2017) based pre-trained models, termed as deep self-attention distillation. The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher). Specifically, we propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Furthermore, we introduce the scaled dot-product between values in the self-attention module as the new deep self-attention knowledge, in addition to the attention distributions (i.e., the scaled dot-product of queries and keys) that have been used in existing works. Moreover, we show that introducing a teacher assistant (Mirzadeh et al., 2019) also helps the distillation of large pre-trained Transformer models. Experimental results demonstrate that our monolingual model outperforms state-of-the-art baselines in different parameter size of student models. In particular, it retains more than 99% accuracy on SQuAD 2.0 and several GLUE benchmark tasks using 50% of the Transformer parameters and computations of the teacher model. We also obtain competitive results in applying deep self-attention distillation to multilingual pre-trained models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search

To speed up the inference of neural speech synthesis, non-autoregressive models receive increasing attention recently. In non-autoregressive models, additional durations of text tokens are required to make a hard alignment between the encoder and the decoder. The duration-based alignment plays a crucial role since it controls the correspondence between text tokens and spectrum frames and determines the rhythm and speed of synthesized audio. To get better duration-based alignment and improve the quality of non-autoregressive speech synthesis, in this paper, we propose a novel neural alignment model named MoboAligner. Given the pairs of the text and mel spectrum, MoboAligner tries to identify the boundaries of text tokens in the given mel spectrum frames based on the token-frame similarity in the neural semantic space with an end-to-end framework. With these boundaries, durations can be extracted and used in the training of non-autoregressive TTS models. Compared with the duration extracted by TransformerTTS, MoboAligner brings improvement for the non-autoregressive TTS model on MOS (3.74 comparing to FastSpeech's 3.44). Besides, MoboAligner is task-specified and lightweight, which reduces the parameter number by 45% and the training time consuming by 30%.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at \url{https://github.com/apexrl/CoDAIL}.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MuTual: A Dataset for Multi-Turn Dialogue Reasoning

Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and fluent response, but sometimes make logical mistakes because of weak reasoning capabilities. To facilitate the conversation reasoning research, we introduce MuTual, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams. Compared to previous benchmarks for non-task oriented dialogue systems, MuTual is much more challenging since it requires a model that can handle various reasoning problems. Empirical results show that state-of-the-art methods only reach 71%, which is far behind the human performance of 94%, indicating that there is ample room for improving reasoning ability. MuTual is available at https://github.com/Nealcly/MuTual.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Pre-training Text Representations as Meta Learning

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for subsequent tasks. However, existing approaches are optimized by minimizing a proxy objective, such as the negative log likelihood of language modeling. In this work, we introduce a learning algorithm which directly optimizes model's ability to learn text representations for effective learning of downstream tasks. We show that there is an intrinsic connection between multi-task pre-training and model-agnostic meta-learning with a sequence of meta-train steps. The standard multi-task learning objective adopted in BERT is a special case of our learning algorithm where the depth of meta-train is zero. We study the problem in two settings: unsupervised pre-training and supervised pre-training with different pre-training objects to verify the generality of our approach.Experimental results show that our algorithm brings improvements and learns better initializations for a variety of downstream tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Reasoning Over Semantic-Level Graph for Fact Checking

Fact checking is a challenging task because verifying the truthfulness of a claim requires reasoning about multiple retrievable evidence. In this work, we present a method suitable for reasoning about the semantic-level structure of evidence. Unlike most previous works, which typically represent evidence sentences with either string concatenation or fusing the features of isolated evidence sentences, our approach operates on rich semantic structures of evidence obtained by semantic role labeling. We propose two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet. Specifically, using XLNet as the backbone, we first utilize the graph structure to re-define the relative distances of words, with the intuition that semantically related words should have short distances. Then, we adopt graph convolutional network and graph attention network to propagate and aggregate information from neighboring nodes on the graph. We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy. Our model is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Self-Adversarial Learning with Comparative Discrimination for Text Generation

Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. In contrast to standard GANs that use a binary classifier as its discriminator to predict whether a sample is real or generated, SAL employs a comparative discriminator which is a pairwise classifier for comparing the text quality between a pair of samples. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. This self-improvement reward mechanism allows the model to receive credits more easily and avoid collapsing towards the limited number of real samples, which not only helps alleviate the reward sparsity issue but also reduces the risk of mode collapse. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity, and yields more stable performance compared to the previous GANs for text generation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Semantic Mask for Transformer based End-to-End Speech Recognition

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the mapping from the input sequence to the output sequence from scratch, without the assumption of prior knowledge such as the alignments. However, this model is prone to overfitting, especially when the amount of training data is limited. Inspired by SpecAugment and BERT, in this paper, we propose a semantic mask based regularization for training such kind of end-to-end (E2E) model. The idea is to mask the input features corresponding to a particular output token, e.g., a word or a word-piece, in order to encourage the model to fill the token based on the contextual information. While this approach is applicable to the encoder-decoder framework with any type of neural network architecture, we study the transformer-based model for ASR in this work. We perform experiments on Librispeech 960h and TedLium2 data sets, and achieve the state-of-the-art performance on the test set in the scope of E2E models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Statistical Issues and Recommendations for Clinical Trials Conducted During the COVID-19 Pandemic

The COVID-19 pandemic has had and continues to have major impacts on planned and ongoing clinical trials. Its effects on trial data create multiple potential statistical issues. The scale of impact is unprecedented, but when viewed individually, many of the issues are well defined and feasible to address. A number of strategies and recommendations are put forward to assess and address issues related to estimands, missing data, validity and modifications of statistical analysis methods, need for additional analyses, ability to meet objectives and overall trial interpretability.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TableBank: A Benchmark Dataset for Table Detection and Recognition

We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually fine-tunes pre-trained models on out-of-domain data with a few thousand human-labeled examples, which is difficult to generalize on real-world applications. With TableBank that contains 417K high quality labeled tables, we build several strong baselines using state-of-the-art models with deep neural networks. We make TableBank publicly available and hope it will empower more deep learning approaches in the table detection and recognition task. The dataset and models are available at \url{https://github.com/doc-analysis/TableBank}.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreover, conventional masks used for autoencoding provide global masking information, so that all the position embeddings are accessible in partially autoregressive language modeling. In addition, the two tasks pre-train a unified language model as a bidirectional encoder and a sequence-to-sequence decoder, respectively. Our experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of natural language understanding and generation tasks across several widely used benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation

In this paper, we introduce XGLUE, a new benchmark dataset that can be used to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora and evaluate their performance across a diverse set of cross-lingual tasks. Comparing to GLUE(Wang et al., 2019), which is labeled in English for natural language understanding tasks only, XGLUE has two main advantages: (1) it provides 11 diversified tasks that cover both natural language understanding and generation scenarios; (2) for each task, it provides labeled data in multiple languages. We extend a recent cross-lingual pre-trained model Unicoder(Huang et al., 2019) to cover both understanding and generation tasks, which is evaluated on XGLUE as a strong baseline. We also evaluate the base versions (12-layer) of Multilingual BERT, XLM and XLM-R for comparison.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

XGPT: Cross-modal Generative Pre-Training for Image Captioning

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new method of Cross-modal Generative Pre-Training for Image Captioning that is designed to pre-train text-to-image caption generators through three novel generation tasks, including Image-conditioned Masked Language Modeling (IMLM), Image-conditioned Denoising Autoencoding (IDA), and Text-conditioned Image Feature Generation (TIFG). As a result, the pre-trained XGPT can be fine-tuned without any task-specific architecture modifications to create state-of-the-art models for image captioning. Experiments show that XGPT obtains new state-of-the-art results on the benchmark datasets, including COCO Captions and Flickr30k Captions. We also use XGPT to generate new image captions as data augmentation for the image retrieval task and achieve significant improvement on all recall metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A mixture evolution scenario of the AGN radio luminosity function

We propose a mixture evolution scenario to model the evolution of the radio luminosity function (RLF) of steep spectrum AGNs (active galactic nuclei) based on a Bayesian method. In this scenario, the shape of the RLF is determined by both the density and luminosity evolution. Our models indicate that the density evolution is positive until a redshift of $\thicksim 0.9$, at which point it becomes negative, while the luminosity evolution is positive to a higher redshift ($z \thicksim 5$ for model B and $z \thicksim 3.5$ for model C), where it becomes negative. Our mixture evolution model works well, and the modeled RLFs are in good agreement with previous determinations. The mixture evolution scenario can naturally explain the luminosity-dependent evolution of the RLFs.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment

Aligning coordinated text streams from multiple sources and multiple languages has opened many new research venues on cross-lingual knowledge discovery. In this paper we aim to advance state-of-the-art by: (1). extending coarse-grained topic-level knowledge mining to fine-grained information units such as entities and events; (2). following a novel Data-to-Network-to-Knowledge (D2N2K) paradigm to construct and utilize network structures to capture and propagate reliable evidence. We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus. We propose an effective approach to construct and decipher BINets, incorporating novel criteria based on multi-dimensional clues from pronunciation, translation, burst, neighbor and graph topological structure. The experimental results on Chinese and English coordinated text streams show that our approach can accurately decipher the nodes with high confidence in the BINets and that the algorithm can be efficiently run in parallel, which makes it possible to apply it to huge amounts of streaming data for never-ending language and information decipherment.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Detecting Context Dependent Messages in a Conversational Environment

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task is challenging, as messages in a conversational environment are short and informal, and evidence that can indicate a message is context dependent is scarce. After a study of social conversation data crawled from the web, we observed that some characteristics estimated from the responses of messages are discriminative for identifying context dependent messages. With the characteristics as weak supervision, we propose using a Long Short Term Memory (LSTM) network to learn a classifier. Our method carries out text representation and classifier learning in a unified framework. Experimental results show that the proposed method can significantly outperform baseline methods on accuracy of classification.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Effect of spectral index distribution on estimating the AGN radio luminosity function

In this paper, we scrutinize the effect of spectral index distribution on estimating the AGN (active galactic nucleus) radio luminosity function (RLF) by a Monte Carlo method. We find that the traditional bivariate RLF estimators can cause bias in varying degree. The bias is especially pronounced for the flat-spectrum radio sources whose spectral index distribution is more scattered. We believe that the bias is caused because the $K$-corrections complicate the truncation boundary on the $L-z$ plane of the sample, but the traditional bivariate RLF estimators have difficulty in dealing with this boundary condition properly. We suggest that the spectral index distribution should be incorporated into the RLF analysis process to obtain a robust estimation. This drives the need for a trivariate function of the form $Φ(α,z,L)$ which we show provides an accurate basis for measuring the RLF.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model

Neural machine translation has shown very promising results lately. Most NMT models follow the encoder-decoder framework. To make encoder-decoder models more flexible, attention mechanism was introduced to machine translation and also other tasks like speech recognition and image captioning. We observe that the quality of translation by attention-based encoder-decoder can be significantly damaged when the alignment is incorrect. We attribute these problems to the lack of distortion and fertility models. Aiming to resolve these problems, we propose new variations of attention-based encoder-decoder and compare them with other models on machine translation. Our proposed method achieved an improvement of 2 BLEU points over the original attention-based encoder-decoder.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Knowledge Enhanced Hybrid Neural Network for Text Matching

Long text brings a big challenge to semantic matching due to their complicated semantic and syntactic structures. To tackle the challenge, we consider using prior knowledge to help identify useful information and filter out noise to matching in long text. To this end, we propose a knowledge enhanced hybrid neural network (KEHNN). The model fuses prior knowledge into word representations by knowledge gates and establishes three matching channels with words, sequential structures of sentences given by Gated Recurrent Units (GRU), and knowledge enhanced representations. The three channels are processed by a convolutional neural network to generate high level features for matching, and the features are synthesized as a matching score by a multilayer perceptron. The model extends the existing methods by conducting matching on words, local structures of sentences, and global context of sentences. Evaluation results from extensive experiments on public data sets for question answering and conversation show that KEHNN can significantly outperform the-state-of-the-art matching models and particularly improve the performance on pairs with long text.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Response Selection with Topic Clues for Retrieval-based Chatbots

We consider incorporating topic information into message-response matching to boost responses with rich content in retrieval-based chatbots. To this end, we propose a topic-aware convolutional neural tensor network (TACNTN). In TACNTN, matching between a message and a response is not only conducted between a message vector and a response vector generated by convolutional neural networks, but also leverages extra topic information encoded in two topic vectors. The two topic vectors are linear combinations of topic words of the message and the response respectively, where the topic words are obtained from a pre-trained LDA model and their weights are determined by themselves as well as the message vector and the response vector. The message vector, the response vector, and the two topic vectors are fed to neural tensors to calculate a matching score. Empirical study on a public data set and a human annotated data set shows that TACNTN can significantly outperform state-of-the-art methods for message-response matching.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Topic Aware Neural Response Generation

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model utilizes topics to simulate prior knowledge of human that guides them to form informative and interesting responses in conversation, and leverages the topic information in generation by a joint attention mechanism and a biased generation probability. The joint attention mechanism summarizes the hidden vectors of an input message as context vectors by message attention, synthesizes topic vectors by topic attention from the topic words of the message obtained from a pre-trained LDA model, and let these vectors jointly affect the generation of words in decoding. To increase the possibility of topic words appearing in responses, the model modifies the generation probability of topic words by adding an extra probability item to bias the overall distribution. Empirical study on both automatic evaluation metrics and human annotations shows that TA-Seq2Seq can generate more informative and interesting responses, and significantly outperform the-state-of-the-art response generation models.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction

In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. The basic idea is to connect two words (w1 and w2) with the dependency path (r) between them in the embedding space. Specifically, our method optimizes the objective w1 + r = w2 in the low-dimensional space, where the multi-hop dependency paths are treated as a sequence of grammatical relations and modeled by a recurrent neural network. Then, we design the embedding features that consider linear context and dependency context information, for the conditional random field (CRF) based aspect term extraction. Experimental results on the SemEval datasets show that, (1) with only embedding features, we can achieve state-of-the-art results; (2) our embedding method which incorporates the syntactic information among words yields better performance than other representative ones in aspect term extraction.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A Dependency-Based Neural Network for Relation Classification

Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees. In this paper, we further explore how to make full use of the combination of these dependency information. We first propose a new structure, termed augmented dependency path (ADP), which is composed of the shortest dependency path between two entities and the subtrees attached to the shortest path. To exploit the semantic representation behind the ADP structure, we develop dependency-based neural networks (DepNN): a recursive neural network designed to model the subtrees, and a convolutional neural network to capture the most important features on the shortest path. Experiments on the SemEval-2010 dataset show that our proposed method achieves state-of-art results.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A Statistical Parsing Framework for Sentiment Classification

We present a statistical parsing framework for sentence-level sentiment classification in this article. Unlike previous works that employ syntactic parsing results for sentiment analysis, we develop a statistical parser to directly analyze the sentiment structure of a sentence. We show that complicated phenomena in sentiment analysis (e.g., negation, intensification, and contrast) can be handled the same as simple and straightforward sentiment expressions in a unified and probabilistic way. We formulate the sentiment grammar upon Context-Free Grammars (CFGs), and provide a formal description of the sentiment parsing framework. We develop the parsing model to obtain possible sentiment parse trees for a sentence, from which the polarity model is proposed to derive the sentiment strength and polarity, and the ranking model is dedicated to selecting the best sentiment tree. We train the parser directly from examples of sentences annotated only with sentiment polarity labels but without any syntactic annotations or polarity annotations of constituents within sentences. Therefore we can obtain training data easily. In particular, we train a sentiment parser, s.parser, from a large amount of review sentences with users' ratings as rough sentiment polarity labels. Extensive experiments on existing benchmark datasets show significant improvements over baseline sentiment classification approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Beyond Word-based Language Model in Statistical Machine Translation

Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target language sentences by rendering and compositing the phrases rather than the words. Thus, it is much more reasonable to model dependency between phrases, but few research work succeed in solving this problem. In this paper, we tackle this problem by designing a novel phrase-based language model which attempts to solve three key sub-problems: 1, how to define a phrase in language model; 2, how to determine the phrase boundary in the large-scale monolingual data in order to enlarge the training set; 3, how to alleviate the data sparsity problem due to the huge vocabulary size of phrases. By carefully handling these issues, the extensive experiments on Chinese-to-English translation show that our phrase-based language model can significantly improve the translation quality by up to +1.47 absolute BLEU score.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

High-efficiency and low-jitter Silicon single-photon avalanche diodes based on nanophotonic absorption enhancement

Silicon single-photon avalanche diode (SPAD) is a core device for single-photon detection in the visible and the near-infrared range, and widely used in many applications. However, due to limits of the structure design and device fabrication for current silicon SPADs, the key parameters of detection befficiency and timing jitter are often forced to compromise. Here, we propose a nanostructured silicon SPAD, which achieves high detection efficiency with excellent timing jitter simultaneously over a broad spectral range. The optical and electric simulations show significant performance enhancement compared with conventional silicon SPAD devices. This nanostructured devices can be easily fabricated and thus well suited for practical applications.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Jointly Modeling Topics and Intents with Global Order Structure

Modeling document structure is of great importance for discourse analysis and related applications. The goal of this research is to capture the document intent structure by modeling documents as a mixture of topic words and rhetorical words. While the topics are relatively unchanged through one document, the rhetorical functions of sentences usually change following certain orders in discourse. We propose GMM-LDA, a topic modeling based Bayesian unsupervised model, to analyze the document intent structure cooperated with order information. Our model is flexible that has the ability to combine the annotations and do supervised learning. Additionally, entropic regularization can be introduced to model the significant divergence between topics and intents. We perform experiments in both unsupervised and supervised settings, results show the superiority of our model over several state-of-the-art baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Multi-Document Summarization via Discriminative Summary Reranking

Existing multi-document summarization systems usually rely on a specific summarization model (i.e., a summarization method with a specific parameter setting) to extract summaries for different document sets with different topics. However, according to our quantitative analysis, none of the existing summarization models can always produce high-quality summaries for different document sets, and even a summarization model with good overall performance may produce low-quality summaries for some document sets. On the contrary, a baseline summarization model may produce high-quality summaries for some document sets. Based on the above observations, we treat the summaries produced by different summarization models as candidate summaries, and then explore discriminative reranking techniques to identify high-quality summaries from the candidates for difference document sets. We propose to extract a set of candidate summaries for each document set based on an ILP framework, and then leverage Ranking SVM for summary reranking. Various useful features have been developed for the reranking process, including word-level features, sentence-level features and summary-level features. Evaluation results on the benchmark DUC datasets validate the efficacy and robustness of our proposed approach.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

TGSum: Build Tweet Guided Multi-Document Summarization Dataset

The development of summarization research has been significantly hampered by the costly acquisition of reference summaries. This paper proposes an effective way to automatically collect large scales of news-related multi-document summaries with reference to social media's reactions. We utilize two types of social labels in tweets, i.e., hashtags and hyper-links. Hashtags are used to cluster documents into different topic sets. Also, a tweet with a hyper-link often highlights certain key points of the corresponding document. We synthesize a linked document cluster to form a reference summary which can cover most key points. To this aim, we adopt the ROUGE metrics to measure the coverage ratio, and develop an Integer Linear Programming solution to discover the sentence set reaching the upper bound of ROUGE. Since we allow summary sentences to be selected from both documents and high-quality tweets, the generated reference summaries could be abstractive. Both informativeness and readability of the collected summaries are verified by manual judgment. In addition, we train a Support Vector Regression summarizer on DUC generic multi-document summarization benchmarks. With the collected data as extra training resource, the performance of the summarizer improves a lot on all the test sets. We release this dataset for further research.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

A New Result on the Origin of the Extragalactic Gamma-ray Background

In the paper, we continually use the method of image stacking to study the origin of the extragalactic gamma-ray background (EGB) at GeV bands, and find that the Faint Images of the Radio Sky at Twenty centimeters (FIRST) sources undetected by the Large Area Telescope on the Fermi Gamma-ray Space Telescope can contribute about (56{plus minus}6)% of the EGB. Because the FIRST is a flux limited sample of radio sources with incompleteness at the faint limit, we consider that the point-sources, including blazars, non-blazar AGNs,starburst galaxies, could produce a much larger fraction of the EGB.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

On the external photon fields in Fermi bright blazars

The external Compton (EC) model is used to study the high energy emission of some blazars, in which the external photon field is considered to dominate inverse Compton radiation. We explore the properties of external photon field through analyzing the FERMI LAT bright AGN sample within three months detection. In the sample, assuming the high energy radiation of low synchrotron peaked blazars from the EC process, we find that the external photon parameter Uext/\nuext may not be a constant. Calculating synchrotron and inverse Compton (IC) luminosity from the quasi-simultaneous broadband spectrum energy distributions (SEDs), we find that they have an approximately linear relation. This indicates that the ratio of external photon and magnetic energy density is a constant in the comoving frame, implying that the Lorentz factor of the emitting blob depends on external photon field and magnetic field. The result gives a strong constraint on the jet dynamic model.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

User-level sentiment analysis incorporating social networks

We show that information about social relationships can be used to improve user-level sentiment analysis. The main motivation behind our approach is that users that are somehow "connected" may be more likely to hold similar opinions; therefore, relationship information can complement what we can extract about a user's viewpoints from their utterances. Employing Twitter as a source for our experimental data, and working within a semi-supervised framework, we propose models that are induced either from the Twitter follower/followee network or from the network in Twitter formed by users referring to each other using "@" mentions. Our transductive learning results reveal that incorporating social-network information can indeed lead to statistically significant sentiment-classification improvements over the performance of an approach based on Support Vector Machines having access only to textual features.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

A New Method to Study the Origin of the EGB and the First Application on AT20G

In this letter, we introduce a new method of image stacking to directly study the undetected but possible gamma-ray point sources. Applying the method to the Australia Telescope 20 GHz Survey (AT20G) sources which have not been detected by LAT on Fermi, we find that the sources contribute (10.5+/-1.1)% and (4.3+/-0.9)% of the extragalactic gamma-ray background (EGB) and have a very soft spectrum with the photon indexes of 3.09+/-0.23 and 2.61+/-0.26, in the 1-3 and 3-300GeV energy ranges. In the 0.1-1GeV range, they probably contribute more large faction to the EGB, but it is not quite sure. It maybe not appropriate to assume that the undetected sources have the similar property to the detected sources.

0 citations0 reviewsNo code linkedOpen access