{"list":"other","total":52,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"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":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"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":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235},{"id":"1705.00652","title":"Efficient Natural Language Response Suggestion for Smart Reply","created":"2017-05-01","cited_by_count":229},{"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":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162},{"id":"1906.07348","title":"Zero-Shot Entity Linking by Reading Entity Descriptions","created":"2019-06-18","cited_by_count":124},{"id":"1909.10506","title":"Learning Dense Representations for Entity Retrieval","created":"2019-09-23","cited_by_count":122},{"id":"1911.03814","title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","created":"2019-11-10","cited_by_count":85},{"id":"2008.00051","title":"On the Convergence of SGD with Biased Gradients","created":"2020-07-31","cited_by_count":83},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"1703.07370","title":"REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models","created":"2017-03-21","cited_by_count":79},{"id":"1303.1849","title":"Revisiting the Nystrom Method for Improved Large-Scale Machine Learning","created":"2013-03-07","cited_by_count":77},{"id":"2006.08063","title":"Gradient Estimation with Stochastic Softmax Tricks","created":"2020-06-15","cited_by_count":67},{"id":"2106.00882","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","created":"2021-06-02","cited_by_count":53},{"id":"2010.05878","title":"PECOS: Prediction for Enormous and Correlated Output Spaces","created":"2020-10-12","cited_by_count":50},{"id":"1712.00527","title":"Adaptive Sampled Softmax with Kernel Based Sampling","created":"2017-12-02","cited_by_count":38},{"id":"1907.10747","title":"Sampled Softmax with Random Fourier Features","created":"2019-07-24","cited_by_count":33},{"id":"2005.12021","title":"Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach","created":"2020-05-25","cited_by_count":30},{"id":"1810.07076","title":"Stochastic Negative Mining for Learning with Large Output Spaces","created":"2018-10-16","cited_by_count":29},{"id":"2109.01242","title":"Entity Linking and Discovery via Arborescence-based Supervised Clustering","created":"2021-09-02","cited_by_count":22},{"id":"2103.05028","title":"Fast and Effective Biomedical Entity Linking Using a Dual Encoder","created":"2021-03-08","cited_by_count":16},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15},{"id":"1412.5721","title":"An Algorithm for Online K-Means Clustering","created":"2014-12-18","cited_by_count":12},{"id":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12},{"id":"1610.04658","title":"Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation","created":"2016-10-14","cited_by_count":10},{"id":"2106.07352","title":"MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network","created":"2021-06-02","cited_by_count":10},{"id":"1406.1822","title":"Logarithmic Time Online Multiclass prediction","created":"2014-06-06","cited_by_count":7},{"id":"1909.09667","title":"Online Hierarchical Clustering Approximations","created":"2019-09-20","cited_by_count":7},{"id":"1606.04988","title":"Logarithmic Time One-Against-Some","created":"2016-06-15","cited_by_count":6},{"id":"2206.11654","title":"Hierarchical Agglomerative Graph Clustering in Poly-Logarithmic Depth","created":"2022-06-23","cited_by_count":6},{"id":"1304.4327","title":"Tree-Independent Dual-Tree Algorithms","created":"2013-04-16","cited_by_count":5},{"id":"1807.06473","title":"Contextual Memory Trees","created":"2018-07-17","cited_by_count":5},{"id":"2007.04451","title":"Online probabilistic label trees","created":"2020-07-08","cited_by_count":5},{"id":"2210.07893","title":"Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees","created":"2022-10-14","cited_by_count":5},{"id":"2004.10915","title":"Doubly-stochastic mining for heterogeneous retrieval","created":"2020-04-23","cited_by_count":4},{"id":"1501.05222","title":"Plug-and-play dual-tree algorithm runtime analysis","created":"2015-01-21","cited_by_count":3},{"id":"1810.10738","title":"Batch-Parallel Euler Tour Trees","created":"2018-10-25","cited_by_count":2},{"id":"1908.01956","title":"Parallel Batch-Dynamic Graphs: Algorithms and Lower Bounds","created":"2019-08-06","cited_by_count":1}],"next_cursor":null}