{"total":331,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2102.05152","title":"On Explainability of Graph Neural Networks via Subgraph Explorations","created":"2021-02-09","cited_by_count":281,"area":null},{"id":"2102.09554","title":"Delving into Deep Imbalanced Regression","created":"2021-02-18","cited_by_count":158,"area":null},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2112.00911","title":"ProtGNN: Towards Self-Explaining Graph Neural Networks","created":"2021-12-02","cited_by_count":96,"area":null},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95,"area":null},{"id":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"area":null},{"id":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62,"area":null},{"id":"2107.12214","title":"Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction","created":"2021-07-26","cited_by_count":60,"area":null},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58,"area":null},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2204.08109","title":"ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering","created":"2022-04-17","cited_by_count":48,"area":null},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2206.05238","title":"Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction","created":"2022-06-10","cited_by_count":46,"area":null},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43,"area":null},{"id":"2109.11503","title":"Finding a Balanced Degree of Automation for Summary Evaluation","created":"2021-09-23","cited_by_count":43,"area":null},{"id":"2201.12380","title":"GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games","created":"2022-01-28","cited_by_count":42,"area":null},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2109.07446","title":"When Does Translation Require Context? A Data-driven, Multilingual Exploration","created":"2021-09-15","cited_by_count":36,"area":null},{"id":"2109.13070","title":"Controllable Neural Dialogue Summarization with Personal Named Entity Planning","created":"2021-09-27","cited_by_count":36,"area":null},{"id":"2212.10409","title":"ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2210.07109","title":"Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2106.14373","title":"A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition","created":"2021-06-28","cited_by_count":33,"area":null},{"id":"2209.03549","title":"Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization","created":"2022-09-08","cited_by_count":32,"area":null},{"id":"2106.06830","title":"Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2104.00430","title":"Latent Space Data Assimilation by using Deep Learning","created":"2021-04-01","cited_by_count":30,"area":null},{"id":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2204.12164","title":"CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets","created":"2022-04-26","cited_by_count":29,"area":null},{"id":"2104.06952","title":"The Surprising Performance of Simple Baselines for Misinformation Detection","created":"2021-04-14","cited_by_count":28,"area":null},{"id":"2105.07911","title":"SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising","created":"2021-05-17","cited_by_count":27,"area":null},{"id":"2204.10432","title":"Improving the Generalizability of Depression Detection by Leveraging Clinical Questionnaires","created":"2022-04-21","cited_by_count":27,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2102.08345","title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2204.01098","title":"A sequence-to-sequence approach for document-level relation extraction","created":"2022-04-03","cited_by_count":25,"area":null},{"id":"2101.09525","title":"Dictionary-based Debiasing of Pre-trained Word Embeddings","created":"2021-01-23","cited_by_count":24,"area":null},{"id":"2106.09233","title":"De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention","created":"2021-06-17","cited_by_count":24,"area":null},{"id":"2209.04280","title":"F-coref: Fast, Accurate and Easy to Use Coreference Resolution","created":"2022-09-09","cited_by_count":24,"area":null},{"id":"2106.14726","title":"Keyphrase Generation for Scientific Document Retrieval","created":"2021-06-28","cited_by_count":23,"area":null},{"id":"2109.04832","title":"Asking It All: Generating Contextualized Questions for any Semantic Role","created":"2021-09-10","cited_by_count":22,"area":null},{"id":"2202.07856","title":"The NLP Task Effectiveness of Long-Range Transformers","created":"2022-02-16","cited_by_count":22,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2109.03160","title":"How much pretraining data do language models need to learn syntax?","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2109.04367","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2109.07954","title":"Improving Unsupervised Question Answering via Summarization-Informed Question Generation","created":"2021-09-16","cited_by_count":21,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2112.08544","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","created":"2021-12-16","cited_by_count":20,"area":null},{"id":"2104.03879","title":"COVID-19 Named Entity Recognition for Vietnamese","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2104.08618","title":"EXTRACTOR: Extracting Attack Behavior from Threat Reports","created":"2021-04-17","cited_by_count":19,"area":null},{"id":"2106.01560","title":"CitationIE: Leveraging the Citation Graph for Scientific Information Extraction","created":"2021-06-03","cited_by_count":19,"area":null},{"id":"2111.00701","title":"Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections","created":"2021-11-01","cited_by_count":19,"area":null},{"id":"2112.08812","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","created":"2021-12-16","cited_by_count":19,"area":null},{"id":"2203.01282","title":"py-irt: A Scalable Item Response Theory Library for Python","created":"2022-03-02","cited_by_count":19,"area":null},{"id":"2203.16279","title":"Neural Pipeline for Zero-Shot Data-to-Text Generation","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19,"area":null},{"id":"2305.15676","title":"Enhancing Grammatical Error Correction Systems with Explanations","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2104.08457","title":"Moving on from OntoNotes: Coreference Resolution Model Transfer","created":"2021-04-17","cited_by_count":18,"area":null},{"id":"2112.08656","title":"DREAM: Improving Situational QA by First Elaborating the Situation","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2304.04415","title":"Meta Compositional Referring Expression Segmentation","created":"2023-04-10","cited_by_count":18,"area":null},{"id":"2101.04922","title":"EventPlus: A Temporal Event Understanding Pipeline","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2102.00405","title":"BNLP: Natural language processing toolkit for Bengali language","created":"2021-01-31","cited_by_count":17,"area":null},{"id":"2207.01079","title":"DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles","created":"2022-07-03","cited_by_count":17,"area":null},{"id":"2303.00595","title":"A Universal Question-Answering Platform for Knowledge Graphs","created":"2023-03-01","cited_by_count":17,"area":null},{"id":"2504.19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation","created":"2025-04-27","cited_by_count":17,"area":null},{"id":"2505.19694","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","created":"2025-05-26","cited_by_count":17,"area":null},{"id":"2106.02569","title":"Neural semi-Markov CRF for Monolingual Word Alignment","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2109.06798","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","created":"2021-09-14","cited_by_count":16,"area":null},{"id":"2101.11177","title":"LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction","created":"2021-01-27","cited_by_count":15,"area":null},{"id":"2109.07848","title":"The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation","created":"2021-09-16","cited_by_count":15,"area":null},{"id":"2109.09777","title":"DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection","created":"2021-09-20","cited_by_count":15,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2106.04530","title":"Learning from Multiple Noisy Partial Labelers","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2109.02865","title":"Journalistic Guidelines Aware News Image Captioning","created":"2021-09-07","cited_by_count":14,"area":null},{"id":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13,"area":null},{"id":"2106.08037","title":"The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2406.07955","title":"How Interpretable Are Interpretable Graph Neural Networks?","created":"2024-06-12","cited_by_count":13,"area":null},{"id":"2107.00807","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","created":"2021-07-02","cited_by_count":12,"area":null},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","cited_by_count":12,"area":null}],"next_cursor":"100"}