{"list":"other","total":77,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"1909.03546","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","created":"2019-09-08","cited_by_count":262},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2004.12265","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","created":"2020-04-26","cited_by_count":191},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1802.00614","title":"Visual Interpretability for Deep Learning: a Survey","created":"2018-02-02","cited_by_count":155},{"id":"1909.01380","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","created":"2019-09-03","cited_by_count":139},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"1801.06889","title":"Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers","created":"2018-01-21","cited_by_count":117},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"2002.06755","title":"Unifying Graph Convolutional Neural Networks and Label Propagation","created":"2020-02-17","cited_by_count":98},{"id":"1903.07435","title":"The emergence of number and syntax units in LSTM language models","created":"2019-03-18","cited_by_count":94},{"id":"1910.07124","title":"FewRel 2.0: Towards More Challenging Few-Shot Relation Classification","created":"2019-10-16","cited_by_count":94},{"id":"2005.07310","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","created":"2020-05-15","cited_by_count":90},{"id":"2006.15222","title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models","created":"2020-06-26","cited_by_count":85},{"id":"2009.09191","title":"OpenAttack: An Open-source Textual Adversarial Attack Toolkit","created":"2020-09-19","cited_by_count":84},{"id":"2004.13826","title":"Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks","created":"2020-04-22","cited_by_count":77},{"id":"1906.03538","title":"Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims","created":"2019-06-08","cited_by_count":74},{"id":"1909.09251","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","created":"2019-09-19","cited_by_count":74},{"id":"2003.04985","title":"Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT","created":"2020-02-27","cited_by_count":69},{"id":"1904.08939","title":"Understanding Neural Networks via Feature Visualization: A survey","created":"2019-04-18","cited_by_count":65},{"id":"1909.13078","title":"OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction","created":"2019-09-28","cited_by_count":62},{"id":"1704.01942","title":"ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models","created":"2017-04-06","cited_by_count":56},{"id":"2009.07053","title":"Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models","created":"2020-09-03","cited_by_count":49},{"id":"1710.10777","title":"Understanding Hidden Memories of Recurrent Neural Networks","created":"2017-10-30","cited_by_count":44},{"id":"2010.05419","title":"Gradient-based Analysis of NLP Models is Manipulable","created":"2020-10-12","cited_by_count":41},{"id":"2005.01641","title":"A Tale of a Probe and a Parser","created":"2020-05-04","cited_by_count":40},{"id":"2003.11755","title":"A Survey of Deep Learning for Scientific Discovery","created":"2020-03-26","cited_by_count":36},{"id":"2009.01523","title":"A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports","created":"2020-09-03","cited_by_count":35},{"id":"2001.11316","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","created":"2020-01-30","cited_by_count":26},{"id":"1703.00565","title":"Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ","created":"2017-03-02","cited_by_count":22},{"id":"1909.13705","title":"A Closer Look at Data Bias in Neural Extractive Summarization Models","created":"2019-09-30","cited_by_count":18},{"id":"2002.04815","title":"Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference","created":"2020-02-12","cited_by_count":14},{"id":"2005.00396","title":"Identifying Necessary Elements for BERT's Multilinguality","created":"2020-05-01","cited_by_count":9},{"id":"2006.09109","title":"How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation","created":"2020-06-16","cited_by_count":7},{"id":"2004.01628","title":"Weighted Random Search for Hyperparameter Optimization","created":"2020-04-03","cited_by_count":6},{"id":"2004.10102","title":"Attention is Not Only a Weight: Analyzing Transformers with Vector Norms","created":"2020-04-21","cited_by_count":6},{"id":"2011.04507","title":"VisBERT: Hidden-State Visualizations for Transformers","created":"2020-11-09","cited_by_count":6},{"id":"1906.01702","title":"Improving Neural Language Models by Segmenting, Attending, and Predicting the Future","created":"2019-06-04","cited_by_count":5},{"id":"1908.00588","title":"Visualizing RNN States with Predictive Semantic Encodings","created":"2019-08-01","cited_by_count":4},{"id":"1912.10169","title":"A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings","created":"2019-12-15","cited_by_count":4},{"id":"2002.09084","title":"On the impressive performance of randomly weighted encoders in summarization tasks","created":"2020-02-21","cited_by_count":3},{"id":"2005.05716","title":"AttViz: Online exploration of self-attention for transparent neural language modeling","created":"2020-05-12","cited_by_count":2}],"next_cursor":null}