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

Jimmy Lin

Jimmy Lin contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Information RetrievalComputation and LanguageMachine LearningArtificial IntelligenceDigital LibrariesDistributed, Parallel, and Cluster Computingphysics.ao-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
32works
0followers
7topics
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

32 published item(s)

preprint2026arXiv

A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation

Evaluation leaderboards such as LMArena play a central role in benchmarking large language models by aggregating pairwise human preferences into model rankings, yet the robustness of these rankings remains poorly understood. We present a unified perturbation framework for analyzing Bradley-Terry leaderboards under structured data modifications using influence-based approximations. Our framework studies three match-level perturbations -- Drop, Add, and Flip -- together with player removal, and evaluates their effects on top-k membership, global ranking consistency via Kendall's tau, and confidence-interval-based uncertainty. Across Chatbot Arena and six additional pairwise-comparison datasets, we show that modern leaderboards are non-robust across all three objectives: sub-1% targeted perturbations can change the top-ranked model, degrade Kendall's tau, and alter confidence intervals. Beyond robustness auditing, we show that the same influence scores enable efficient targeted perturbations, promoting or demoting specific models and reducing target-model uncertainty with fewer actions than previous manipulation and active-sampling baselines. By summarizing these effects with normalized dataset-level robustness scores, our framework provides a practical and helpful tool for auditing leaderboard stability and motivating more robust evaluation protocols.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning. Agentic tasks further exacerbate this limitation because they require agents to orchestrate multiple steps, including discovering intermediate entities, combining weak clues, and revising the plan after observing partial evidence. To tackle the limitation, we study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools (e.g., grep, file reads, shell commands, lightweight scripts), without any embedding model, vector index, or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines on several BRIGHT and BEIR datasets, and attains strong accuracy on BrowseComp-Plus and multi-hop QA without relying on any conventional semantic retriever. Our results indicate that as language agents become stronger, retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus, with which DCI opens a broader interface-design space for agentic search.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum

While dense retrieval models have become the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GPU accelerators for vector similarity search. Learned sparse retrieval offers a compelling alternative by enabling efficient search via inverted indices, yet it has historically received less attention than dense approaches. In this report, we introduce LACONIC, a family of learned sparse retrievers based on the Llama-3 architecture (1B, 3B, and 8B). We propose a streamlined two-phase training curriculum consisting of (1) weakly supervised pre-finetuning to adapt causal LLMs for bidirectional contextualization and (2) high-signal finetuning using curated hard negatives. Our results demonstrate that LACONIC effectively bridges the performance gap with dense models: the 8B variant achieves a state-of-the-art 60.2 nDCG on the MTEB Retrieval benchmark, ranking 15th on the leaderboard as of January 1, 2026, while utilizing 71\% less index memory than an equivalent dense model. By delivering high retrieval effectiveness on commodity CPU hardware with a fraction of the compute budget required by competing models, LACONIC provides a scalable and efficient solution for real-world search applications.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building deep research systems. We revisit it by pairing BM25 with frontier LLMs that have better reasoning and tool-use abilities. To support researchers asking the same question, we introduce Pi-Serini, a search agent equipped with three tools for retrieving, browsing, and reading documents. Our results show that, on BrowseComp-Plus, a well-configured lexical retriever with sufficient retrieval depth can support effective deep research when paired with more capable LLMs. Specifically, Pi-Serini with gpt-5.5 achieves 83.1% answer accuracy and 94.7% surfaced evidence recall, outperforming released search agents that use dense retrievers. Controlled ablations further show that BM25 tuning improves answer accuracy by 18.0% and surfaced evidence recall by 11.1% over the default BM25 setting, while increasing retrieval depth further improves surfaced evidence recall by 25.3% over the shallow-retrieval setting. Source code is available at https://github.com/justram/pi-serini.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges

This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevance judges are all highly vulnerable to attacks that enable arbitrary content to be promoted to the top of search results and to be assigned perfect relevance scores. We investigate how attackers may achieve this via content injection, injecting arbitrary sentences into relevant passages or query terms into arbitrary passages. Our study analyzes how factors such as model class and size, the balance between relevant and non-relevant content, injection location, toxicity and severity of injected content, and the role of LLM-generated content influence attack success, yielding novel, concerning, and often counterintuitive results. Our results reveal a weakness in embedding models, LLM-based scoring models, and generative LLMs, raising concerns about the general robustness, safety, and trustworthiness of language models regardless of the type of model or the role in which they are employed. We also emphasize the challenges of robust defenses against these attacks. Classifiers and more carefully prompted LLM judges often fail to recognize passages with content injection, especially when considering diverse text topics and styles. Our findings highlight the need for further research into arbitrary content injection attacks. We release our code for further study.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Which Model Shall I Choose? Cost/Quality Trade-offs for Text Classification Tasks

Industry practitioners always face the problem of choosing the appropriate model for deployment under different considerations, such as to maximize a metric that is crucial for production, or to reduce the total cost given financial concerns. In this work, we focus on the text classification task and present a quantitative analysis for this challenge. Using classification accuracy as the main metric, we evaluate the classifiers' performances for a variety of models, including large language models, along with their associated costs, including the annotation cost, training (fine-tuning) cost, and inference cost. We then discuss the model choices for situations like having a large number of samples needed for inference. We hope our work will help people better understand the cost/quality trade-offs for the text classification task.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers

There exists a wide variety of efficiency methods for natural language processing (NLP) tasks, such as pruning, distillation, dynamic inference, quantization, etc. We can consider an efficiency method as an operator applied on a model. Naturally, we may construct a pipeline of multiple efficiency methods, i.e., to apply multiple operators on the model sequentially. In this paper, we study the plausibility of this idea, and more importantly, the commutativity and cumulativeness of efficiency operators. We make two interesting observations: (1) Efficiency operators are commutative -- the order of efficiency methods within the pipeline has little impact on the final results; (2) Efficiency operators are also cumulative -- the final results of combining several efficiency methods can be estimated by combining the results of individual methods. These observations deepen our understanding of efficiency operators and provide useful guidelines for their real-world applications.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Can Old TREC Collections Reliably Evaluate Modern Neural Retrieval Models?

Neural retrieval models are generally regarded as fundamentally different from the retrieval techniques used in the late 1990's when the TREC ad hoc test collections were constructed. They thus provide the opportunity to empirically test the claim that pooling-built test collections can reliably evaluate retrieval systems that did not contribute to the construction of the collection (in other words, that such collections can be reusable). To test the reusability claim, we asked TREC assessors to judge new pools created from new search results for the TREC-8 ad hoc collection. These new search results consisted of five new runs (one each from three transformer-based models and two baseline runs that use BM25) plus the set of TREC-8 submissions that did not previously contribute to pools. The new runs did retrieve previously unseen documents, but the vast majority of those documents were not relevant. The ranking of all runs by mean evaluation score when evaluated using the official TREC-8 relevance judgment set and the newly expanded relevance set are almost identical, with Kendall's tau correlations greater than 0.99. Correlations for individual topics are also high. The TREC-8 ad hoc collection was originally constructed using deep pools over a diverse set of runs, including several effective manual runs. Its judgment budget, and hence construction cost, was relatively large. However, it does appear that the expense was well-spent: even with the advent of neural techniques, the collection has stood the test of time and remains a reliable evaluation instrument as retrieval techniques have advanced.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking

In information retrieval (IR), candidate set pruning has been commonly used to speed up two-stage relevance ranking. However, such an approach lacks accurate error control and often trades accuracy off against computational efficiency in an empirical fashion, lacking theoretical guarantees. In this paper, we propose the concept of certified error control of candidate set pruning for relevance ranking, which means that the test error after pruning is guaranteed to be controlled under a user-specified threshold with high probability. Both in-domain and out-of-domain experiments show that our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed while satisfying the pre-specified accuracy constraints in both settings. For example, on MS MARCO Passage v1, our method yields an average candidate set size of 27 out of 1,000 which increases the reranking speed by about 37 times, while the MRR@10 is greater than a pre-specified value of 0.38 with about 90% empirical coverage and the empirical baselines fail to provide such guarantee. Code and data are available at: https://github.com/alexlimh/CEC-Ranking.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval

Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of them come with their own software stacks. These stacks are typically optimized for some particular research goals instead of efficiency or code structure. In this paper, we present Tevatron, a dense retrieval toolkit optimized for efficiency, flexibility, and code simplicity. Tevatron provides a standardized pipeline for dense retrieval including text processing, model training, corpus/query encoding, and search. This paper presents an overview of Tevatron and demonstrates its effectiveness and efficiency across several IR and QA data sets. We also show how Tevatron's flexible design enables easy generalization across datasets, model architectures, and accelerator platforms(GPU/TPU). We believe Tevatron can serve as an effective software foundation for dense retrieval system research including design, modeling, and optimization.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Best Practices for Training Multilingual Dense Retrieval Models

Dense retrieval models using a transformer-based bi-encoder design have emerged as an active area of research. In this work, we focus on the task of monolingual retrieval in a variety of typologically diverse languages using one such design. Although recent work with multilingual transformers demonstrates that they exhibit strong cross-lingual generalization capabilities, there remain many open research questions, which we tackle here. Our study is organized as a "best practices" guide for training multilingual dense retrieval models, broken down into three main scenarios: where a multilingual transformer is available, but relevance judgments are not available in the language of interest; where both models and training data are available; and, where training data are available not but models. In considering these scenarios, we gain a better understanding of the role of multi-stage fine-tuning, the strength of cross-lingual transfer under various conditions, the usefulness of out-of-language data, and the advantages of multilingual vs. monolingual transformers. Our recommendations offer a guide for practitioners building search applications, particularly for low-resource languages, and while our work leaves open a number of research questions, we provide a solid foundation for future work.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Don't Change Me! User-Controllable Selective Paraphrase Generation

In the paraphrase generation task, source sentences often contain phrases that should not be altered. Which phrases, however, can be context dependent and can vary by application. Our solution to this challenge is to provide the user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" when generating a paraphrase; the model learns to explicitly copy these phrases to the output. The contribution of this work is a novel data generation technique using distant supervision that allows us to start with a pretrained sequence-to-sequence model and fine-tune a paraphrase generator that exhibits this behavior, allowing user-controllable paraphrase generation. Additionally, we modify the loss during fine-tuning to explicitly encourage diversity in model output. Our technique is language agnostic, and we report experiments in English and Chinese.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations

Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture. Our toolkit is self-contained as a standard Python package and comes with queries, relevance judgments, pre-built indexes, and evaluation scripts for many commonly used IR test collections. We aim to support, out of the box, the entire research lifecycle of efforts aimed at improving ranking with modern neural approaches. In particular, Pyserini supports sparse retrieval (e.g., BM25 scoring using bag-of-words representations), dense retrieval (e.g., nearest-neighbor search on transformer-encoded representations), as well as hybrid retrieval that integrates both approaches. This paper provides an overview of toolkit features and presents empirical results that illustrate its effectiveness on two popular ranking tasks. We also describe how our group has built a culture of replicability through shared norms and tools that enable rigorous automated testing.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard

Leaderboards are a ubiquitous part of modern research in applied machine learning. By design, they sort entries into some linear order, where the top-scoring entry is recognized as the "state of the art" (SOTA). Due to the rapid progress being made in information retrieval today, particularly with neural models, the top entry in a leaderboard is replaced with some regularity. These are touted as improvements in the state of the art. Such pronouncements, however, are almost never qualified with significance testing. In the context of the MS MARCO document ranking leaderboard, we pose a specific question: How do we know if a run is significantly better than the current SOTA? We ask this question against the backdrop of recent IR debates on scale types: in particular, whether commonly used significance tests are even mathematically permissible. Recognizing these potential pitfalls in evaluation methodology, our study proposes an evaluation framework that explicitly treats certain outcomes as distinct and avoids aggregating them into a single-point metric. Empirical analysis of SOTA runs from the MS MARCO document ranking leaderboard reveals insights about how one run can be "significantly better" than another that are obscured by the current official evaluation metric (MRR@100).

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models

We propose a design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains. At the core, our design relies on pretrained sequence-to-sequence models within a standard multi-stage ranking architecture. "Expando" refers to the use of document expansion techniques to enrich keyword representations of texts prior to inverted indexing. "Mono" and "Duo" refer to components in a reranking pipeline based on a pointwise model and a pairwise model that rerank initial candidates retrieved using keyword search. We present experimental results from the MS MARCO passage and document ranking tasks, the TREC 2020 Deep Learning Track, and the TREC-COVID challenge that validate our design. In all these tasks, we achieve effectiveness that is at or near the state of the art, in some cases using a zero-shot approach that does not exploit any training data from the target task. To support replicability, implementations of our design pattern are open-sourced in the Pyserini IR toolkit and PyGaggle neural reranking library.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Data Scientist's Guide to Streamflow Prediction

In recent years, the paradigms of data-driven science have become essential components of physical sciences, particularly in geophysical disciplines such as climatology. The field of hydrology is one of these disciplines where machine learning and data-driven models have attracted significant attention. This offers significant potential for data scientists' contributions to hydrologic research. As in every interdisciplinary research effort, an initial mutual understanding of the domain is key to successful work later on. In this work, we focus on the element of hydrologic rainfall--runoff models and their application to forecast floods and predict streamflow, the volume of water flowing in a river. This guide aims to help interested data scientists gain an understanding of the problem, the hydrologic concepts involved, and the details that come up along the way. We have captured lessons that we have learned while "coming up to speed" on streamflow prediction and hope that our experiences will be useful to the community.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Prototype of Serverless Lucene

This paper describes a working prototype that adapts Lucene, the world's most popular and most widely deployed open-source search library, to operate within a serverless environment in the cloud. Although the serverless search concept is not new, this work represents a substantial improvement over a previous implementation in eliminating most custom code and in enabling interactive search. While there remain limitations to the design, it nevertheless challenges conventional thinking about search architectures for particular operating points.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. In CQR benchmarks of task-oriented dialogue systems, we evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task. Examining a variety of architectures with different numbers of parameters, we demonstrate that the recent text-to-text transfer transformer (T5) achieves the best results both on CANARD and CAsT with fewer parameters, compared to similar transformer architectures.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset

We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI. Our system has been online and serving users since late March 2020. The Covidex is the user application component of our three-pronged strategy to develop technologies for helping domain experts tackle the ongoing global pandemic. In addition, we provide robust and easy-to-use keyword search infrastructure that exploits mature fusion-based methods as well as standalone neural ranking models that can be incorporated into other applications. These techniques have been evaluated in the ongoing TREC-COVID challenge: Our infrastructure and baselines have been adopted by many participants, including some of the highest-scoring runs in rounds 1, 2, and 3. In round 3, we report the highest-scoring run that takes advantage of previous training data and the second-highest fully automatic run.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We propose a simple but effective method, DeeBERT, to accelerate BERT inference. Our approach allows samples to exit earlier without passing through the entire model. Experiments show that DeeBERT is able to save up to ~40% inference time with minimal degradation in model quality. Further analyses show different behaviors in the BERT transformer layers and also reveal their redundancy. Our work provides new ideas to efficiently apply deep transformer-based models to downstream tasks. Code is available at https://github.com/castorini/DeeBERT.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Document Ranking with a Pretrained Sequence-to-Sequence Model

This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the task of document ranking. Our approach is fundamentally different from a commonly-adopted classification-based formulation of ranking, based on encoder-only pretrained transformer architectures such as BERT. We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words", and how the underlying logits of these target words can be interpreted as relevance probabilities for ranking. On the popular MS MARCO passage ranking task, experimental results show that our approach is at least on par with previous classification-based models and can surpass them with larger, more-recent models. On the test collection from the TREC 2004 Robust Track, we demonstrate a zero-shot transfer-based approach that outperforms previous state-of-the-art models requiring in-dataset cross-validation. Furthermore, we find that our approach significantly outperforms an encoder-only model in a data-poor regime (i.e., with few training examples). We investigate this observation further by varying target words to probe the model's use of latent knowledge.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Howl: A Deployed, Open-Source Wake Word Detection System

We describe Howl, an open-source wake word detection toolkit with native support for open speech datasets, like Mozilla Common Voice and Google Speech Commands. We report benchmark results on Speech Commands and our own freely available wake word detection dataset, built from MCV. We operationalize our system for Firefox Voice, a plugin enabling speech interactivity for the Firefox web browser. Howl represents, to the best of our knowledge, the first fully productionized yet open-source wake word detection toolkit with a web browser deployment target. Our codebase is at https://github.com/castorini/howl.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a light-weight student model. So far the distillation approaches are all task-specific. In this paper, we explore knowledge distillation under the multi-task learning setting. The student is jointly distilled across different tasks. It acquires more general representation capacity through multi-tasking distillation and can be further fine-tuned to improve the model in the target domain. Unlike other BERT distillation methods which specifically designed for Transformer-based architectures, we provide a general learning framework. Our approach is model agnostic and can be easily applied on different future teacher model architectures. We evaluate our approach on a Transformer-based and LSTM based student model. Compared to a strong, similarly LSTM-based approach, we achieve better quality under the same computational constraints. Compared to the present state of the art, we reach comparable results with much faster inference speed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation

Citation recommendation systems for the scientific literature, to help authors find papers that should be cited, have the potential to speed up discoveries and uncover new routes for scientific exploration. We treat this task as a ranking problem, which we tackle with a two-stage approach: candidate generation followed by re-ranking. Within this framework, we adapt to the scientific domain a proven combination based on "bag of words" retrieval followed by re-scoring with a BERT model. We experimentally show the effects of domain adaptation, both in terms of pretraining on in-domain data and exploiting in-domain vocabulary. In addition, we introduce a novel navigation-based document expansion strategy to enrich the candidate documents processed by our neural models. On three different collections from different scientific disciplines, we achieve the best-reported results in the citation recommendation task.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents

Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than "standard" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than 100 documents) are sufficient to achieve reasonable accuracy. We integrate our models into an end-to-end cloud platform that provides both an easy-to-use annotation interface as well as an inference interface that allows users to upload documents and inspect model outputs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rapidly Bootstrapping a Question Answering Dataset for COVID-19

We present CovidQA, the beginnings of a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered from Kaggle's COVID-19 Open Research Dataset Challenge. To our knowledge, this is the first publicly available resource of its type, and intended as a stopgap measure for guiding research until more substantial evaluation resources become available. While this dataset, comprising 124 question-article pairs as of the present version 0.1 release, does not have sufficient examples for supervised machine learning, we believe that it can be helpful for evaluating the zero-shot or transfer capabilities of existing models on topics specifically related to COVID-19. This paper describes our methodology for constructing the dataset and presents the effectiveness of a number of baselines, including term-based techniques and various transformer-based models. The dataset is available at http://covidqa.ai/

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned

We present the Neural Covidex, a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI. This web application exists as part of a suite of tools that we have developed over the past few weeks to help domain experts tackle the ongoing global pandemic. We hope that improved information access capabilities to the scientific literature can inform evidence-based decision making and insight generation. This paper describes our initial efforts and offers a few thoughts about lessons we have learned along the way.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Showing Your Work Doesn't Always Work

In natural language processing, a recently popular line of work explores how to best report the experimental results of neural networks. One exemplar publication, titled "Show Your Work: Improved Reporting of Experimental Results," advocates for reporting the expected validation effectiveness of the best-tuned model, with respect to the computational budget. In the present work, we critically examine this paper. As far as statistical generalizability is concerned, we find unspoken pitfalls and caveats with this approach. We analytically show that their estimator is biased and uses error-prone assumptions. We find that the estimator favors negative errors and yields poor bootstrapped confidence intervals. We derive an unbiased alternative and bolster our claims with empirical evidence from statistical simulation. Our codebase is at http://github.com/castorini/meanmax.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Supporting Interoperability Between Open-Source Search Engines with the Common Index File Format

There exists a natural tension between encouraging a diverse ecosystem of open-source search engines and supporting fair, replicable comparisons across those systems. To balance these two goals, we examine two approaches to providing interoperability between the inverted indexes of several systems. The first takes advantage of internal abstractions around index structures and building wrappers that allow one system to directly read the indexes of another. The second involves sharing indexes across systems via a data exchange specification that we have developed, called the Common Index File Format (CIFF). We demonstrate the first approach with the Java systems Anserini and Terrier, and the second approach with Anserini, JASSv2, OldDog, PISA, and Terrier. Together, these systems provide a wide range of implementations and features, with different research goals. Overall, we recommend CIFF as a low-effort approach to support independent innovation while enabling the types of fair evaluations that are critical for driving the field forward.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The Archives Unleashed Project: Technology, Process, and Community to Improve Scholarly Access to Web Archives

The Archives Unleashed project aims to improve scholarly access to web archives through a multi-pronged strategy involving tool creation, process modeling, and community building - all proceeding concurrently in mutually-reinforcing efforts. As we near the end of our initially-conceived three-year project, we report on our progress and share lessons learned along the way. The main contribution articulated in this paper is a process model that decomposes scholarly inquiries into four main activities: filter, extract, aggregate, and visualize. Based on the insight that these activities can be disaggregated across time, space, and tools, it is possible to generate "derivative products", using our Archives Unleashed Toolkit, that serve as useful starting points for scholarly inquiry. Scholars can download these products from the Archives Unleashed Cloud and manipulate them just like any other dataset, thus providing access to web archives without requiring any specialized knowledge. Over the past few years, our platform has processed over a thousand different collections from about two hundred users, totaling over 280 terabytes of web archives.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TTTTTackling WinoGrande Schemas

We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using the probabilities assigned to the "entailment" token as a score of the hypothesis. Our first (and only) submission to the official leaderboard yielded 0.7673 AUC on March 13, 2020, which is the best known result at this time and beats the previous state of the art by over five points.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.

0 citations0 reviewsNo code linkedOpen access