{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","cited_by_count":645},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2104.06967","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","created":"2021-04-14","cited_by_count":238},{"id":"2005.00181","title":"Sparse, Dense, and Attentional Representations for Text Retrieval","created":"2020-05-01","cited_by_count":214},{"id":"2108.05540","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","created":"2021-08-12","cited_by_count":203},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176},{"id":"1905.01969","title":"Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","created":"2019-04-22","cited_by_count":165},{"id":"2104.08051","title":"Optimizing Dense Retrieval Model Training with Hard Negatives","created":"2021-04-16","cited_by_count":155},{"id":"2010.02666","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","created":"2020-10-06","cited_by_count":145},{"id":"2109.10086","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","created":"2021-09-21","cited_by_count":127},{"id":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113},{"id":"2012.12624","title":"Learning Dense Representations of Phrases at Scale","created":"2020-12-23","cited_by_count":91},{"id":"2007.00814","title":"Relevance-guided Supervision for OpenQA with ColBERT","created":"2020-07-01","cited_by_count":71},{"id":"2106.14807","title":"A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques","created":"2021-06-28","cited_by_count":69},{"id":"2104.12016","title":"Learning Passage Impacts for Inverted Indexes","created":"2021-04-24","cited_by_count":68},{"id":"2101.00436","title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","created":"2021-01-02","cited_by_count":63},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53},{"id":"2106.00882","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","created":"2021-06-02","cited_by_count":53},{"id":"2107.13602","title":"Domain-matched Pre-training Tasks for Dense Retrieval","created":"2021-07-28","cited_by_count":53},{"id":"2010.11386","title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers","created":"2020-10-22","cited_by_count":52},{"id":"2108.06027","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","created":"2021-08-13","cited_by_count":50},{"id":"2006.15498","title":"RepBERT: Contextualized Text Embeddings for First-Stage Retrieval","created":"2020-06-28","cited_by_count":46},{"id":"2004.14255","title":"Efficient Document Re-Ranking for Transformers by Precomputing Term Representations","created":"2020-04-29","cited_by_count":44},{"id":"2110.07752","title":"Hindsight: Posterior-guided training of retrievers for improved open-ended generation","created":"2021-10-14","cited_by_count":38},{"id":"2108.00644","title":"Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance","created":"2021-08-02","cited_by_count":35},{"id":"1712.02679","title":"AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training","created":"2017-12-07","cited_by_count":33},{"id":"2109.08133","title":"Phrase Retrieval Learns Passage Retrieval, Too","created":"2021-09-16","cited_by_count":33},{"id":"2012.15156","title":"A Memory Efficient Baseline for Open Domain Question Answering","created":"2020-12-30","cited_by_count":32},{"id":"1910.07561","title":"A Double Residual Compression Algorithm for Efficient Distributed Learning","created":"2019-10-16","cited_by_count":31},{"id":"2110.05789","title":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval","created":"2021-10-12","cited_by_count":27},{"id":"2110.07581","title":"Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations","created":"2021-10-14","cited_by_count":27},{"id":"2005.04474","title":"TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection","created":"2020-05-09","cited_by_count":23},{"id":"2010.10469","title":"Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently","created":"2020-10-20","cited_by_count":11},{"id":"2108.11480","title":"On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval","created":"2021-08-25","cited_by_count":7},{"id":"2110.02065","title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","created":"2021-10-03","cited_by_count":7}],"next_cursor":null}