{"list":"other","total":78,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"id":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2007.15207","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","created":"2020-07-30","cited_by_count":153},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2005.00589","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","created":"2020-05-01","cited_by_count":147},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105},{"id":"2012.08668","title":"Mitigating Bias in Calibration Error Estimation","created":"2020-12-15","cited_by_count":101},{"id":"1908.05803","title":"Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning","created":"2019-08-16","cited_by_count":100},{"id":"2106.01515","title":"Question Answering Over Temporal Knowledge Graphs","created":"2021-06-03","cited_by_count":99},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52},{"id":"1910.02216","title":"JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation","created":"2019-10-05","cited_by_count":49},{"id":"1705.00823","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","created":"2017-05-02","cited_by_count":47},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"1907.00490","title":"ICDAR 2019 Competition on Scene Text Visual Question Answering","created":"2019-06-30","cited_by_count":46},{"id":"2104.14336","title":"Document Collection Visual Question Answering","created":"2021-04-27","cited_by_count":45},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37},{"id":"2206.11863","title":"CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking","created":"2022-06-06","cited_by_count":37},{"id":"2005.06376","title":"BIOMRC: A Dataset for Biomedical Machine Reading Comprehension","created":"2020-05-13","cited_by_count":35},{"id":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30},{"id":"2004.11861","title":"Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs","created":"2020-04-24","cited_by_count":26},{"id":"2209.07601","title":"Towards Improving Calibration in Object Detection Under Domain Shift","created":"2022-09-15","cited_by_count":26},{"id":"2004.14283","title":"SubjQA: A Dataset for Subjectivity and Review Comprehension","created":"2020-04-29","cited_by_count":24},{"id":"2104.01569","title":"Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks","created":"2021-04-04","cited_by_count":24},{"id":"1708.05482","title":"A Question Answering Approach to Emotion Cause Extraction","created":"2017-08-18","cited_by_count":21},{"id":"1912.01046","title":"TutorialVQA: Question Answering Dataset for Tutorial Videos","created":"2019-12-02","cited_by_count":20},{"id":"2008.08899","title":"Document Visual Question Answering Challenge 2020","created":"2020-08-20","cited_by_count":20},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19},{"id":"2212.05726","title":"T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics","created":"2022-12-12","cited_by_count":19},{"id":"2206.04045","title":"STable: Table Generation Framework for Encoder-Decoder Models","created":"2022-06-08","cited_by_count":15},{"id":"2109.10604","title":"NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset","created":"2021-09-22","cited_by_count":14},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13},{"id":"1909.08970","title":"RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation","created":"2019-09-19","cited_by_count":11},{"id":"2012.12643","title":"On Calibration of Scene-Text Recognition Models","created":"2020-12-23","cited_by_count":9},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9},{"id":"2210.06852","title":"Overview of BioASQ 2022: The tenth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering","created":"2022-10-13","cited_by_count":9},{"id":"1903.00216","title":"KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos","created":"2019-03-01","cited_by_count":2}],"next_cursor":null}