BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Liang He

Liang He contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageComputer VisionArtificial Intelligencecond-mat.mes-hallcond-mat.quant-gascond-mat.stat-mechMachine Learningcond-mat.softcond-mat.mtrl-scicond-mat.str-elMultimediaphysics.plasm-phquant-phRoboticsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
24works
0followers
15topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

24 published item(s)

preprint2026arXiv

Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems

Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including scientific assistance, long-horizon agents, high-stakes advice, personalization, and tool use, where the relevant objective is ambiguous, context-dependent, delayed, or only partially observable. We argue that many such failures are not merely failures of scale or capability, but failures of objective selection: the system optimizes a locally visible signal while missing which objectives should govern the interaction. We formulate this problem as \emph{contextual multi-objective optimization}. In this setting, systems must consider multiple, context-dependent objectives, such as helpfulness, truthfulness, safety, privacy, calibration, non-manipulation, user preference, reversibility, and stakeholder impact, while determining which objectives are active, which are soft preferences, and which must function as hard or quasi-hard constraints. These examples are not intended as an exhaustive taxonomy: different domains and deployment settings may activate different objective dimensions and different conflict-resolution procedures. Our framework models AI behavior as a context-dependent choice rule over candidate actions, objective estimates, active constraints, stakeholders, uncertainty, and conflict-resolution procedures. We outline an implementation pathway based on decomposed objective representations, context-to-objective routing, hierarchical constraints, deliberative policy reasoning, controlled personalization, tool-use control, diagnostic evaluation, auditing, and post-deployment revision.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis

Structured sentiment analysis, which aims to extract the complex semantic structures such as holders, expressions, targets, and polarities, has obtained widespread attention from both industry and academia. Unfortunately, the existing structured sentiment analysis datasets refer to a few languages and are relatively small, limiting neural network models' performance. In this paper, we focus on the cross-lingual structured sentiment analysis task, which aims to transfer the knowledge from the source language to the target one. Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer. First, we design an adversarial embedding adapter for learning an informative and robust representation by capturing implicit semantic information from diverse multi-lingual embeddings adaptively. Then, we propose a syntax GCN encoder to transfer the explicit semantic information (e.g., universal dependency tree) among multiple languages. We conduct experiments on five datasets and compare \texttt{KEAM} with both the supervised and unsupervised methods. The extensive experimental results show that our \texttt{KEAM} model outperforms all the unsupervised baselines in various metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Survey of Human-in-the-loop for Machine Learning

Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers in the pipeline with the help of machine-based approaches. In this paper, we survey existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: (1) the work of improving model performance from data processing, (2) the work of improving model performance through interventional model training, and (3) the design of the system independent human-in-the-loop. Using the above categorization, we summarize major approaches in the field; along with their technical strengths/ weaknesses, we have simple classification and discussion in natural language processing, computer vision, and others. Besides, we provide some open challenges and opportunities. This survey intends to provide a high-level summarization for human-in-the-loop and motivates interested readers to consider approaches for designing effective human-in-the-loop solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Crystallizing Kagome artificial spin ice

Artificial spin ices are engineered arrays of dipolarly coupled nanobar magnets. They enable direct investigations of fascinating collective phenomena from their diverse microstates. However, experimental access to ground states in the geometrically frustrated systems has proven difficult, limiting studies and applications of novel properties and functionalities from the low energy states. Here, we introduce a convenient approach to control the competing diploar interactions between the neighboring nanomagnets, allowing us to tailor the vertex degeneracy of the ground states. We achieve this by tuning the length of selected nanobar magnets in the spin ice lattice. We demonstrate the effectiveness of our method by realizing multiple low energy microstates in a Kagome artificial spin ice, particularly the hardly accessible long range ordered ground state - the spin crystal state. Our strategy can be directly applied to other artificial spin systems to achieve exotic phases and explore new emergent collective behaviors.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Emergent Mott insulators and non-Hermitian conservation laws in an interacting bosonic chain with noninteger filling and nonreciprocal hopping

We investigate the ground state and quantum dynamics of an interacting bosonic chain with the nonreciprocal hopping. In sharp contrast to its Hermitian counterpart, the ground state can support Mott insulators in systems with noninteger filling due to the competition between nonreciprocal hopping and the on-site interaction. For the quantum dynamics, conservation laws for non-Hermitian systems manifest a stark difference from their Hermitian counterpart. In particular, for any Hermitian operator that commutes with the Hamiltonian operator, its expectation value is guaranteed to be nonconserved in the non-Hermitian quantum dynamics. To systematically identify the non-Hermitian conservation law, we establish a generic approach for constructing the conserved quantities in non-Hermitian many-body quantum systems with completely real spectra, and illustrate it concretely by the system under study. The direct experimental observation of Mott insulators in systems with noninteger filling and non-Hermitian conservation laws can be performed by ultracold atoms in optical lattices with the engineered nonreciprocal hopping.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Enhancing Event-Level Sentiment Analysis with Structured Arguments

Previous studies about event-level sentiment analysis (SA) usually model the event as a topic, a category or target terms, while the structured arguments (e.g., subject, object, time and location) that have potential effects on the sentiment are not well studied. In this paper, we redefine the task as structured event-level SA and propose an End-to-End Event-level Sentiment Analysis ($\textit{E}^{3}\textit{SA}$) approach to solve this issue. Specifically, we explicitly extract and model the event structure information for enhancing event-level SA. Extensive experiments demonstrate the great advantages of our proposed approach over the state-of-the-art methods. Noting the lack of the dataset, we also release a large-scale real-world dataset with event arguments and sentiment labelling for promoting more researches\footnote{The dataset is available at https://github.com/zhangqi-here/E3SA}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Finite temperature mean-field theory with intrinsic non-hermitian structures for Bose gases in optical lattices

We reveal a divergent issue associated with the mean-field theory for Bose gases in optical lattices constructed by the widely used straightforward mean-field decoupling of the hopping term, where the corresponding mean-field Hamiltonian generally assumes no lower energy bound once the spatial dependence of the mean-field superfluid order parameter is taken into account. Via a systematic functional integral approach, we solve this issue by establishing a general finite temperature mean-field theory that can treat any possible spatial dependence of the order parameter without causing the divergent issue. Interestingly, we find the theory generally assumes an intrinsic non-hermitian structure that originates from the indefiniteness of the hopping matrix of the system. Within this theory, we develop an efficient approach for investigating the physics of the system at finite temperature, where properties of the system can be calculated via straightforward investigation on the saddle points of an effective potential function for the order parameter. We illustrate our approach by investigating the finite temperature superfluid transition of Bose gases in optical lattices. Since the underlying finite temperature mean-field theory is quite general, this approach can be straightforwardly applied to investigate the finite temperature properties of related systems with phases possessing complex spatial structures.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

First Identification of New X-Ray Spectra of Mo39+, Mo40+, W43+, W44+ and W45+ on EAST

New high-resolution x-ray spectra of Mo39+, Mo40+, W43+, W44+ and W45+ have been carefully confirmed for the first time by use of the x-ray imaging crystal spectrometer (XCS) in Experimental Advanced Superconducting Tokamak (EAST) under various combined auxiliary heating plasmas conditions. Wavelength of these new x-ray spectra is ranged from 3.895 Å to 3.986 Å. When core electron temperature (Te0) reaches 6.0 keV, Mo39+ and Mo40+ lines of 3.9727, 3.9294 and 3.9480 Å can be effectively detected on XCS for EAST; meanwhile, line-integrated brightness of these spectral lines of Mo39+ and Mo40+ is very considerable when electron temperature reaches 12.9 keV. Multi-components spectral lines for W43+, W44+ and W45+ have also been identified when Te0 reaches 6 keV. Parts of spectral lines, such as Zn-1, Cu-2, Cu-4a, Cu-4d and Cu-5 lines of tungsten, are first observed experimentally. When electron temperature reaches 12.9 keV, line-integrated intensity for part of these spectral lines of W43+, W44+ and W45+ are considerable. These experimental results and theoretical predictions from FAC and FLYCHK codes are in good general agreement. These new spectral lines, obtained on XCS for EAST, are vital for deeply uncovering the mechanisms of ion and electron thermal, high-Z impurity and momentum (anomalous) transport to achieve the advanced steady-state operation scenarios for ITER and CFETR.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Graph Neural Networks with Motif-aware for Tenuous Subgraph Finding

Tenuous subgraph finding aims to detect a subgraph with few social interactions and weak relationships among nodes. Despite significant efforts have been made on this task, they are mostly carried out in view of graph-structured data. These methods depend on calculating the shortest path and need to enumerate all the paths between nodes, which suffer the combinatorial explosion. Moreover, they all lack the integration of neighborhood information. To this end, we propose a novel model named Graph Neural Network with Motif-aware for tenuous subgraph finding (GNNM), a neighborhood aggregation based GNNs framework which can capture the latent relationship between nodes. Specially, we design a GNN module to project nodes into a low dimensional vector combining the higher-order correlation within nodes based on a motif-aware module. And then design greedy algorithms in vector space to obtain a tenuous subgraph whose size is greater than a specified constraint. Particularly, considering existing evaluation indicators cannot capture the latent friendship between nodes, we introduce a novel Potential Friend(PF) concept to measure the tenuity of a graph from a new perspective. Experimental results on the real-world and synthetic datasets demonstrate that our proposed method GNNM outperforms existing algorithms in efficiency and subgraph quality.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis

Nowadays, with the explosive growth of multimodal reviews on social media platforms, multimodal sentiment analysis has recently gained popularity because of its high relevance to these social media posts. Although most previous studies design various fusion frameworks for learning an interactive representation of multiple modalities, they fail to incorporate sentimental knowledge into inter-modality learning. This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion. For cross-modality interactive learning, we exploit the self-attention mechanism combined with densely connected graph convolutional networks to learn inter-modality dynamics. For sentimental feature fusion, we utilize multi-head self-attention to merge sentimental knowledge into inter-modality feature representations. Extensive experiments are conducted on three widely-used datasets. The experimental results demonstrate that the proposed model achieves competitive performance on accuracy and F1 scores compared to several state-of-the-art approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Robot Path Planning Using Medial-Axis-Based Pebble-Graph Embedding

We present a centralized algorithm for labeled, disk-shaped Multi-Robot Path Planning (MPP) in a continuous planar workspace with polygonal boundaries. Our method automatically transform the continuous problem into a discrete, graph-based variant termed the pebble motion problem, which can be solved efficiently. To construct the underlying pebble graph, we identify inscribed circles in the workspace via a medial axis transform and organize robots into layers within each inscribed circle. We show that our layered pebble-graph enables collision-free motions, allowing all graph-restricted MPP instances to be feasible. MPP instances with continuous start and goal positions can then be solved via local navigations that route robots from and to graph vertices. We tested our method on several environments with high robot-packing densities (up to $61.6\%$ of the workspace). For environments with narrow passages, such density violates the well-separated assumptions made by state-of-the-art MPP planners, while our method achieves an average success rate of $83\%$.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Real-space condensation of reciprocal active particles driven by spontaneous symmetry breaking induced nonreciprocity

We investigate the steady-state and dynamical properties of a reciprocal many-body system consisting of self-propelled active particles with local alignment interactions that exists within a fan-shaped neighborhood of each particle. We find that the nonreciprocity can emerge in this reciprocal system once the spontaneous symmetry breaking is present, and the effective description of the system assumes a non-Hermitian structure that directly originates from the emergent nonreciprocity. This emergent nonreciprocity can impose strong influences on the properties the system. In particular, it can even drive a real-space condensation of active particles. Our findings pave the way for identifying a new class of physics in reciprocal systems that is driven by the emergent nonreciprocity.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Scanning-probe and information-concealing machine learning intermediate hexatic phase and critical scaling of solid-hexatic phase transition in deformable particles

We investigate the two-dimensional melting of deformable polymeric particles with multi-body interactions described by the Voronoi model. We report machine learning evidence for the existence of the intermediate hexatic phase in this system, and extract the critical exponent $ν\approx0.65$ for the divergence of the correlation length of the associated solid-hexatic phase transition. Moreover, we clarify the discontinuous nature of the hexatic-liquid phase transition in this system. These findings are achieved by directly analyzing system's spatial configurations with two generic machine learning approaches developed in this work, dubbed "scanning-probe" via which the possible existence of intermediate phases can be efficiently detected, and "information-concealing" via which the critical scaling of the correlation length in the vicinity of generic continuous phase transition can be extracted. Our work provides new physical insights into the fundamental nature of the two-dimensional melting of deformable particles, and establishes a new type of generic toolbox to investigate fundamental properties of phase transitions in various complex systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding

Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to extract visual feature maps independently without considering the query information. We argue that the visual features extracted from the visual backbones and the features really needed for multimodal reasoning are inconsistent. One reason is that there are differences between pre-training tasks and visual grounding. Moreover, since the backbones are query-agnostic, it is difficult to completely avoid the inconsistency issue by training the visual backbone end-to-end in the visual grounding framework. In this paper, we propose a Query-modulated Refinement Network (QRNet) to address the inconsistent issue by adjusting intermediate features in the visual backbone with a novel Query-aware Dynamic Attention (QD-ATT) mechanism and query-aware multiscale fusion. The QD-ATT can dynamically compute query-dependent visual attention at the spatial and channel levels of the feature maps produced by the visual backbone. We apply the QRNet to an end-to-end visual grounding framework. Extensive experiments show that the proposed method outperforms state-of-the-art methods on five widely used datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Document Layout Analysis via Dynamic Residual Feature Fusion

The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval. However, it is a challenge to build a DLA system because the training data is very limited and lacks an efficient model. In this paper, we propose an end-to-end united network named Dynamic Residual Fusion Network (DRFN) for the DLA task. Specifically, we design a dynamic residual feature fusion module which can fully utilize low-dimensional information and maintain high-dimensional category information. Besides, to deal with the model overfitting problem that is caused by lacking enough data, we propose the dynamic select mechanism for efficient fine-tuning in limited train data. We experiment with two challenging datasets and demonstrate the effectiveness of the proposed module.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Giant Topological Hall Effect in van der Waals Heterostructures of CrTe2/Bi2Te3

Discoveries of interfacial topological Hall effect (THE) provide an ideal platform for exploring physics arising from the interplay between topology and magnetism. The interfacial topological Hall effect is closely related to the Dzyaloshinskii-Moriya interaction (DMI) at interface and topological spin textures. However, it is difficult to achieve a sizable THE in heterostructures due to the stringent constraints on the constituents of THE heterostructures such as strong spin-orbit coupling (SOC). Here we report the observation of a giant THE signal of 1.39 $μΩ\cdot$cm in the van der Waals heterostructures of CrTe2/Bi2Te3 fabricated by molecular beam epitaxy, a prototype of two-dimensional (2D) ferromagnet (FM)/topological insulator (TI). This large magnitude of THE is attributed to an optimized combination of 2D ferromagnetism in CrTe2, strong SOC in Bi2Te3, and an atomically sharp interface. Our work reveals CrTe2/Bi2Te3 as a convenient platform for achieving large interfacial THE in hybrid systems, which could be utilized to develop quantum science and high-density information storage.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Real-Time Deep Network for Crowd Counting

Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with the real situation, we hope the model run as fast as possible while keeping accuracy. In this paper, we propose a compact convolutional neural network for crowd counting which learns a more efficient model with a small number of parameters. With three parallel filters executing the convolutional operation on the input image simultaneously at the front of the network, our model could achieve nearly real-time speed and save more computing resources. Experiments on two benchmarks show that our proposed method not only takes a balance between performance and efficiency which is more suitable for actual scenes but also is superior to existing light-weight models in speed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Anomalous thermodynamics of lattice Bose gases in optical cavities

We investigate thermodynamic properties of lattice Bose gases in optical cavities in the Mott-insulator limit. We find the system assumes anomalous thermodynamic behavior that can be traced back to the breaking of fundamental additivity by its infinite-long range interaction. Specifically, the system shows striking ensemble inequivalence between the canonical ensemble and the grand canonical one, sharply manifesting in the distinct anomalous structure of the thermodynamic phase diagram in the canonical ensemble. In particular, in the temperature regime around half of the on-site energy, the system manifests negative compressibility and anomalous reentrant phase transitions where the ordered charge density wave phase revives from the disordered homogenous phase upon increasing the temperature. Direct experimental observation of the anomalous behavior can be realized in the current experiments with well-controlled total particle number fluctuations.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation

This paper describes our system for SemEval-2020 Task 4: Commonsense Validation and Explanation (Wang et al., 2020). We propose a novel Knowledge-enhanced Graph Attention Network (KEGAT) architecture for this task, leveraging heterogeneous knowledge from both the structured knowledge base (i.e. ConceptNet) and unstructured text to better improve the ability of a machine in commonsense understanding. This model has a powerful commonsense inference capability via utilizing suitable commonsense incorporation methods and upgraded data augmentation techniques. Besides, an internal sharing mechanism is cooperated to prohibit our model from insufficient and excessive reasoning for commonsense. As a result, this model performs quite well in both validation and explanation. For instance, it achieves state-of-the-art accuracy in the subtask called Commonsense Explanation (Multi-Choice). We officially name the system as ECNU-SenseMaker. Code is publicly available at https://github.com/ECNU-ICA/ECNU-SenseMaker.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Edge-Aware Deep Image Deblurring

Image deblurring is a fundamental and challenging low-level vision problem. Previous vision research indicates that edge structure in natural scenes is one of the most important factors to estimate the abilities of human visual perception. In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring. An edge detection convolutional subnet is designed in the first phase and a residual fully convolutional deblur subnet is then used for generating deblur results. The introduction of the edge-aware network enables our model with the specific capacity of enhancing images with sharp edges. We successfully apply our framework on standard benchmarks and promising results are achieved by our proposed deblur model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Fast Video Crowd Counting with a Temporal Aware Network

Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting. With the ubiquitous video capture devices in public safety field, how to effectively apply the crowd counting technique to video content has become an urgent problem. In this paper, we introduce a novel framework based on temporal aware modeling of the relationship between video frames. The proposed network contains a few dilated residual blocks, and each of them consists of the layers that compute the temporal convolutions of features from the adjacent frames to improve the prediction. To alleviate the expensive computation and satisfy the demand of fast video crowd counting, we also introduce a lightweight network to balance the computational cost with representation ability. We conduct experiments on the crowd counting benchmarks and demonstrate its superiority in terms of effectiveness and efficiency over previous video-based approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring

Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay. Since obtaining a large quantity of pre-graded essays to a particular prompt is often difficult and unrealistic, the task of cross-prompt AES is vital for the development of real-world AES systems, yet it remains an under-explored area of research. Models designed for prompt-specific AES rely heavily on prompt-specific knowledge and perform poorly in the cross-prompt setting, whereas current approaches to cross-prompt AES either require a certain quantity of labelled target-prompt essays or require a large quantity of unlabelled target-prompt essays to perform transfer learning in a multi-step manner. To address these issues, we introduce Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES. Our method requires no access to labelled or unlabelled target-prompt data during training and is a single-stage approach. PAES is easy to apply in practice and achieves state-of-the-art performance on the Automated Student Assessment Prize (ASAP) dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Scene Text Recognition with Temporal Convolutional Encoder

Texts from scene images typically consist of several characters and exhibit a characteristic sequence structure. Existing methods capture the structure with the sequence-to-sequence models by an encoder to have the visual representations and then a decoder to translate the features into the label sequence. In this paper, we study text recognition framework by considering the long-term temporal dependencies in the encoder stage. We demonstrate that the proposed Temporal Convolutional Encoder with increased sequential extents improves the accuracy of text recognition. We also study the impact of different attention modules in convolutional blocks for learning accurate text representations. We conduct comparisons on seven datasets and the experiments demonstrate the effectiveness of our proposed approach.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SEEK: Segmented Embedding of Knowledge Graphs

In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering. However, existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them still far from satisfactory. To mitigate this problem, we propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity. Our framework focuses on the design of scoring functions and highlights two critical characteristics: 1) facilitating sufficient feature interactions; 2) preserving both symmetry and antisymmetry properties of relations. It is noteworthy that owing to the general and elegant design of scoring functions, our framework can incorporate many famous existing methods as special cases. Moreover, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework. Source codes and data can be found at \url{https://github.com/Wentao-Xu/SEEK}.

0 citations0 reviewsNo code linkedOpen access