{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"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":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"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":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"2010.06467","title":"Pretrained Transformers for Text Ranking: BERT and Beyond","created":"2020-10-13","cited_by_count":267},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"1904.08375","title":"Document Expansion by Query Prediction","created":"2019-04-17","cited_by_count":231},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"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":"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":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162},{"id":"2104.08051","title":"Optimizing Dense Retrieval Model Training with Hard Negatives","created":"2021-04-16","cited_by_count":155},{"id":"2002.03932","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","created":"2020-02-10","cited_by_count":153},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"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":"2010.07003","title":"Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search","created":"2020-10-14","cited_by_count":76},{"id":"1610.08136","title":"Learning to Match Using Local and Distributed Representations of Text for Web Search","created":"2016-10-26","cited_by_count":68},{"id":"2101.08751","title":"Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline","created":"2021-01-21","cited_by_count":65},{"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":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44},{"id":"2010.10137","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2020-10-20","cited_by_count":40},{"id":"2204.07675","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","created":"2022-04-15","cited_by_count":37},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"2210.04457","title":"XPrompt: Exploring the Extreme of Prompt Tuning","created":"2022-10-10","cited_by_count":30},{"id":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","cited_by_count":25},{"id":"2305.12129","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","created":"2023-05-20","cited_by_count":25},{"id":"2204.10641","title":"Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction","created":"2022-04-22","cited_by_count":23},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21},{"id":"2007.11088","title":"Understanding BERT Rankers Under Distillation","created":"2020-07-21","cited_by_count":15},{"id":"2108.09346","title":"Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need","created":"2021-08-20","cited_by_count":15},{"id":"2105.03599","title":"Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval","created":"2021-05-08","cited_by_count":14},{"id":"2210.03923","title":"Sparse Teachers Can Be Dense with Knowledge","created":"2022-10-08","cited_by_count":11},{"id":"2004.11045","title":"Distilling Knowledge for Fast Retrieval-based Chat-bots","created":"2020-04-23","cited_by_count":10},{"id":"2009.07531","title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval","created":"2020-09-16","cited_by_count":10},{"id":"2207.09638","title":"Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets","created":"2022-07-20","cited_by_count":4},{"id":"2305.12330","title":"Task-agnostic Distillation of Encoder-Decoder Language Models","created":"2023-05-21","cited_by_count":4}],"next_cursor":null}