{"list":"other","total":51,"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"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":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"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":"2006.03236","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","created":"2020-06-05","cited_by_count":162},{"id":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162},{"id":"2006.11632","title":"Embedding-based Retrieval in Facebook Search","created":"2020-06-20","cited_by_count":156},{"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":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"1807.05614","title":"ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms","created":"2018-07-15","cited_by_count":130},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98},{"id":"2109.04212","title":"Efficient Nearest Neighbor Language Models","created":"2021-09-09","cited_by_count":93},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83},{"id":"2110.03611","title":"Adversarial Retriever-Ranker for dense text retrieval","created":"2021-10-07","cited_by_count":83},{"id":"2101.12631","title":"A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search","created":"2021-01-29","cited_by_count":82},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"2103.04831","title":"Semantic Models for the First-stage Retrieval: A Comprehensive Review","created":"2021-03-08","cited_by_count":57},{"id":"1907.00937","title":"Semantic Product Search","created":"2019-07-01","cited_by_count":51},{"id":"2010.05878","title":"PECOS: Prediction for Enormous and Correlated Output Spaces","created":"2020-10-12","cited_by_count":50},{"id":"2108.06027","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","created":"2021-08-13","cited_by_count":50},{"id":"2012.14210","title":"The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes","created":"2020-12-28","cited_by_count":48},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41},{"id":"2106.12657","title":"Extreme Multi-label Learning for Semantic Matching in Product Search","created":"2021-06-23","cited_by_count":28},{"id":"1610.03317","title":"A Greedy Approach for Budgeted Maximum Inner Product Search","created":"2016-10-11","cited_by_count":11},{"id":"1810.12406","title":"Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks","created":"2018-10-29","cited_by_count":10},{"id":"2102.06025","title":"Large-Scale Training System for 100-Million Classification at Alibaba","created":"2021-02-09","cited_by_count":10},{"id":"2208.11503","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","created":"2022-08-24","cited_by_count":10},{"id":"2105.02978","title":"Graph-based Multilingual Product Retrieval in E-commerce Search","created":"2021-05-06","cited_by_count":9},{"id":"2110.14943","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","created":"2021-10-28","cited_by_count":6},{"id":"2208.09847","title":"Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval","created":"2022-08-21","cited_by_count":5}],"next_cursor":null}