{"list":"other","total":92,"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"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":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1706.07979","title":"Methods for Interpreting and Understanding Deep Neural Networks","created":"2017-06-24","cited_by_count":345},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1707.06690","title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","created":"2017-07-20","cited_by_count":266},{"id":"2006.11371","title":"Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey","created":"2020-06-16","cited_by_count":254},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"1809.01496","title":"Learning Gender-Neutral Word Embeddings","created":"2018-08-29","cited_by_count":169},{"id":"1711.05851","title":"Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning","created":"2017-11-15","cited_by_count":161},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1808.08949","title":"Dissecting Contextual Word Embeddings: Architecture and Representation","created":"2018-08-27","cited_by_count":146},{"id":"2005.06247","title":"Explainable Reinforcement Learning: A Survey","created":"2020-05-13","cited_by_count":141},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1805.04623","title":"Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context","created":"2018-05-12","cited_by_count":113},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2012.13985","title":"Explaining NLP Models via Minimal Contrastive Editing (MiCE)","created":"2020-12-27","cited_by_count":106},{"id":"1708.03743","title":"Cross-Sentence N-ary Relation Extraction with Graph LSTMs","created":"2017-08-12","cited_by_count":101},{"id":"1808.02610","title":"L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data","created":"2018-08-08","cited_by_count":100},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1803.07416","title":"Tensor2Tensor for Neural Machine Translation","created":"2018-03-16","cited_by_count":85},{"id":"1906.07510","title":"Attention Guided Graph Convolutional Networks for Relation Extraction","created":"2019-06-18","cited_by_count":82},{"id":"1805.02023","title":"Chinese NER Using Lattice LSTM","created":"2018-05-05","cited_by_count":81},{"id":"1409.2574","title":"Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures","created":"2014-09-09","cited_by_count":77},{"id":"1909.11218","title":"Attention Interpretability Across NLP Tasks","created":"2019-09-24","cited_by_count":71},{"id":"1509.06664","title":"Reasoning about Entailment with Neural Attention","created":"2015-09-22","cited_by_count":69},{"id":"1804.09299","title":"Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models","created":"2018-04-25","cited_by_count":69},{"id":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"1912.04971","title":"Neural Module Networks for Reasoning over Text","created":"2019-12-10","cited_by_count":66},{"id":"1901.09813","title":"Analogies Explained: Towards Understanding Word Embeddings","created":"2019-01-28","cited_by_count":64},{"id":"1707.01943","title":"A causal framework for explaining the predictions of black-box sequence-to-sequence models","created":"2017-07-06","cited_by_count":58},{"id":"1711.08792","title":"SPINE: SParse Interpretable Neural Embeddings","created":"2017-11-23","cited_by_count":55},{"id":"1811.00196","title":"Towards Explainable NLP: A Generative Explanation Framework for Text Classification","created":"2018-11-01","cited_by_count":55},{"id":"1808.09367","title":"Deriving Machine Attention from Human Rationales","created":"2018-08-28","cited_by_count":54},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2004.14243","title":"Towards Transparent and Explainable Attention Models","created":"2020-04-29","cited_by_count":47},{"id":"1506.02004","title":"Sparse Overcomplete Word Vector Representations","created":"2015-06-05","cited_by_count":44},{"id":"1803.03585","title":"The Importance of Being Recurrent for Modeling Hierarchical Structure","created":"2018-03-09","cited_by_count":42},{"id":"1602.08952","title":"Representation of linguistic form and function in recurrent neural networks","created":"2016-02-29","cited_by_count":39},{"id":"1605.04469","title":"Rationale-Augmented Convolutional Neural Networks for Text Classification","created":"2016-05-14","cited_by_count":39},{"id":"1805.04218","title":"Deep RNNs Encode Soft Hierarchical Syntax","created":"2018-05-11","cited_by_count":34},{"id":"1910.05276","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","created":"2019-10-11","cited_by_count":33},{"id":"1803.06581","title":"Variational Knowledge Graph Reasoning","created":"2018-03-17","cited_by_count":27},{"id":"1909.12114","title":"Explaining and Interpreting LSTMs","created":"2019-09-25","cited_by_count":23},{"id":"1810.10708","title":"Learning with Interpretable Structure from Gated RNN","created":"2018-10-25","cited_by_count":13},{"id":"1904.08654","title":"Analytical Methods for Interpretable Ultradense Word Embeddings","created":"2019-04-18","cited_by_count":13},{"id":"1708.03390","title":"Making Sense of Word Embeddings","created":"2017-08-10","cited_by_count":12},{"id":"1703.03055","title":"Interpretable Structure-Evolving LSTM","created":"2017-03-08","cited_by_count":9},{"id":"1611.07252","title":"Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery","created":"2016-11-22","cited_by_count":8},{"id":"1909.00504","title":"Rotate King to get Queen: Word Relationships as Orthogonal Transformations in Embedding Space","created":"2019-09-02","cited_by_count":4},{"id":"2008.05925","title":"Commonsense Knowledge Graph Reasoning by Selection or Generation? Why?","created":"2020-08-13","cited_by_count":4}],"next_cursor":null}