{"list":"other","total":61,"rows":[{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2203.13947","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","created":"2022-03-26","cited_by_count":80},{"id":"2007.03875","title":"KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base","created":"2020-07-08","cited_by_count":78},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67},{"id":"2211.07342","title":"MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction","created":"2022-11-14","cited_by_count":66},{"id":"2210.12467","title":"ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts","created":"2022-10-22","cited_by_count":59},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50},{"id":"2110.07474","title":"MReD: A Meta-Review Dataset for Structure-Controllable Text Generation","created":"2021-10-14","cited_by_count":42},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40},{"id":"2211.03433","title":"Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering","created":"2022-11-07","cited_by_count":40},{"id":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","cited_by_count":39},{"id":"2203.13926","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","created":"2022-03-25","cited_by_count":38},{"id":"2211.01355","title":"MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation","created":"2022-11-02","cited_by_count":38},{"id":"2205.11764","title":"D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat","created":"2022-05-24","cited_by_count":37},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36},{"id":"2204.06347","title":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","created":"2022-04-13","cited_by_count":34},{"id":"2110.06884","title":"ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers","created":"2021-10-13","cited_by_count":29},{"id":"2204.13243","title":"HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data","created":"2022-04-28","cited_by_count":28},{"id":"2210.14712","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","created":"2022-10-26","cited_by_count":28},{"id":"2210.07370","title":"M2D2: A Massively Multi-domain Language Modeling Dataset","created":"2022-10-13","cited_by_count":26},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25},{"id":"2203.12257","title":"IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks","created":"2022-03-23","cited_by_count":23},{"id":"2302.03815","title":"Long Text and Multi-Table Summarization: Dataset and Method","created":"2023-02-08","cited_by_count":23},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22},{"id":"2210.09345","title":"CrossRE: A Cross-Domain Dataset for Relation Extraction","created":"2022-10-17","cited_by_count":21},{"id":"2211.16496","title":"TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages","created":"2022-11-29","cited_by_count":21},{"id":"2211.05955","title":"MEE: A Novel Multilingual Event Extraction Dataset","created":"2022-11-11","cited_by_count":17},{"id":"2202.13645","title":"MSCTD: A Multimodal Sentiment Chat Translation Dataset","created":"2022-02-28","cited_by_count":15},{"id":"2210.14814","title":"BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples","created":"2022-10-26","cited_by_count":15},{"id":"2211.04872","title":"Visual Named Entity Linking: A New Dataset and A Baseline","created":"2022-11-09","cited_by_count":15},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14},{"id":"2211.00869","title":"Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset","created":"2022-11-02","cited_by_count":14},{"id":"2210.12687","title":"BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets","created":"2022-10-23","cited_by_count":13},{"id":"2211.10018","title":"A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach","created":"2022-11-18","cited_by_count":13},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12},{"id":"2205.12215","title":"DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages","created":"2022-05-24","cited_by_count":11},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11},{"id":"2211.07980","title":"A Benchmark and Dataset for Post-OCR text correction in Sanskrit","created":"2022-11-15","cited_by_count":10},{"id":"2210.12096","title":"Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play","created":"2022-10-21","cited_by_count":9},{"id":"2210.17378","title":"Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency","created":"2022-10-31","cited_by_count":9},{"id":"2202.12459","title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","created":"2022-02-25","cited_by_count":8},{"id":"2203.14498","title":"EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English","created":"2022-03-28","cited_by_count":7},{"id":"2210.04573","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","created":"2022-10-10","cited_by_count":7},{"id":"2210.12401","title":"PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text","created":"2022-10-22","cited_by_count":6},{"id":"2112.08808","title":"Simple Questions Generate Named Entity Recognition Datasets","created":"2021-12-16","cited_by_count":5},{"id":"2212.06049","title":"CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation","created":"2022-11-16","cited_by_count":5},{"id":"2112.08609","title":"DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models","created":"2021-12-16","cited_by_count":4},{"id":"2205.10843","title":"Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce","created":"2022-05-22","cited_by_count":4},{"id":"2212.04357","title":"A Fine-grained Chinese Software Privacy Policy Dataset for Sequence Labeling and Regulation Compliant Identification","created":"2022-12-04","cited_by_count":3},{"id":"2112.06733","title":"Measuring Context-Word Biases in Lexical Semantic Datasets","created":"2021-12-13","cited_by_count":1},{"id":"2301.06617","title":"ClassBases at CASE-2022 Multilingual Protest Event Detection Tasks: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets","created":"2023-01-16","cited_by_count":1}],"next_cursor":null}