{"list":"other","total":73,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2005.08314","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","created":"2020-05-17","cited_by_count":398},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1909.04164","title":"Knowledge Enhanced Contextual Word Representations","created":"2019-09-09","cited_by_count":296},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1804.06059","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","created":"2018-04-17","cited_by_count":286},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"2009.13845","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","created":"2020-09-29","cited_by_count":171},{"id":"2010.10439","title":"Open Question Answering over Tables and Text","created":"2020-10-20","cited_by_count":163},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2008.02637","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","created":"2020-08-06","cited_by_count":138},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"2012.12627","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","created":"2020-12-23","cited_by_count":133},{"id":"2005.00628","title":"Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?","created":"2020-05-01","cited_by_count":127},{"id":"1811.07039","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","created":"2018-11-16","cited_by_count":120},{"id":"2105.02584","title":"TABBIE: Pretrained Representations of Tabular Data","created":"2021-05-06","cited_by_count":111},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"1912.09637","title":"Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model","created":"2019-12-20","cited_by_count":102},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87},{"id":"2005.06117","title":"INFOTABS: Inference on Tables as Semi-structured Data","created":"2020-05-13","cited_by_count":86},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82},{"id":"1906.07241","title":"Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling","created":"2019-06-17","cited_by_count":71},{"id":"2010.00571","title":"Understanding tables with intermediate pre-training","created":"2020-10-01","cited_by_count":68},{"id":"1904.02668","title":"Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets","created":"2019-04-04","cited_by_count":42},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39},{"id":"1906.00041","title":"Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval","created":"2019-05-31","cited_by_count":37},{"id":"2005.04732","title":"Towards Robustifying NLI Models Against Lexical Dataset Biases","created":"2020-05-10","cited_by_count":34},{"id":"2104.08303","title":"Capturing Row and Column Semantics in Transformer Based Question Answering over Tables","created":"2021-04-16","cited_by_count":31},{"id":"1811.07033","title":"Analyzing Compositionality-Sensitivity of NLI Models","created":"2018-11-16","cited_by_count":26},{"id":"2005.01218","title":"Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering","created":"2020-05-04","cited_by_count":24},{"id":"2203.14278","title":"StruBERT: Structure-aware BERT for Table Search and Matching","created":"2022-03-27","cited_by_count":24},{"id":"2104.04243","title":"Incorporating External Knowledge to Enhance Tabular Reasoning","created":"2021-04-09","cited_by_count":23},{"id":"2101.10573","title":"Representations for Question Answering from Documents with Tables and Text","created":"2021-01-26","cited_by_count":21},{"id":"2005.11490","title":"Summarizing and Exploring Tabular Data in Conversational Search","created":"2020-05-23","cited_by_count":19},{"id":"2109.04223","title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","created":"2021-09-09","cited_by_count":19},{"id":"2002.00207","title":"Web Table Extraction, Retrieval and Augmentation: A Survey","created":"2020-02-01","cited_by_count":15},{"id":"2104.01099","title":"TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training","created":"2021-04-02","cited_by_count":14},{"id":"2108.00578","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","created":"2021-08-02","cited_by_count":9},{"id":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4},{"id":"2108.00603","title":"TabPert: An Effective Platform for Tabular Perturbation","created":"2021-08-02","cited_by_count":2}],"next_cursor":null}