{"list":"other","total":60,"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"1904.08082","title":"Self-Attention Graph Pooling","created":"2019-04-17","cited_by_count":421},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"2001.06216","title":"GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks","created":"2020-01-17","cited_by_count":209},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"1909.00505","title":"Commonsense Knowledge Mining from Pretrained Models","created":"2019-09-02","cited_by_count":189},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"2005.00646","title":"Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering","created":"2020-05-01","cited_by_count":122},{"id":"2010.05607","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","created":"2020-10-12","cited_by_count":122},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"2009.12677","title":"KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning","created":"2020-09-26","cited_by_count":106},{"id":"2010.04119","title":"Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?","created":"2020-10-08","cited_by_count":95},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"1909.05311","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","created":"2019-09-09","cited_by_count":68},{"id":"1904.01172","title":"Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches","created":"2019-04-02","cited_by_count":65},{"id":"1412.6815","title":"Extraction of Salient Sentences from Labelled Documents","created":"2014-12-21","cited_by_count":50},{"id":"1809.05724","title":"Improving Natural Language Inference Using External Knowledge in the Science Questions Domain","created":"2018-09-15","cited_by_count":48},{"id":"2004.14243","title":"Towards Transparent and Explainable Attention Models","created":"2020-04-29","cited_by_count":47},{"id":"2005.00691","title":"Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering","created":"2020-05-02","cited_by_count":44},{"id":"1711.04289","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","created":"2017-11-12","cited_by_count":40},{"id":"1602.08952","title":"Representation of linguistic form and function in recurrent neural networks","created":"2016-02-29","cited_by_count":39},{"id":"1910.14087","title":"Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering","created":"2019-10-30","cited_by_count":37},{"id":"1811.07882","title":"Guiding Policies with Language via Meta-Learning","created":"2018-11-19","cited_by_count":35},{"id":"1905.13714","title":"Do Human Rationales Improve Machine Explanations?","created":"2019-05-31","cited_by_count":33},{"id":"2011.05268","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","created":"2020-10-24","cited_by_count":30},{"id":"1808.03894","title":"Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference","created":"2018-08-12","cited_by_count":26},{"id":"2012.09157","title":"LIREx: Augmenting Language Inference with Relevant Explanation","created":"2020-12-16","cited_by_count":24},{"id":"2005.09379","title":"Staying True to Your Word: (How) Can Attention Become Explanation?","created":"2020-05-19","cited_by_count":18},{"id":"2010.12873","title":"Learning Contextualized Knowledge Structures for Commonsense Reasoning","created":"2020-10-24","cited_by_count":18},{"id":"1810.07528","title":"Machine Common Sense Concept Paper","created":"2018-10-17","cited_by_count":17},{"id":"1911.03876","title":"Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering","created":"2019-11-10","cited_by_count":16},{"id":"2010.12872","title":"Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation","created":"2020-10-24","cited_by_count":10},{"id":"2005.05240","title":"Commonsense Evidence Generation and Injection in Reading Comprehension","created":"2020-05-11","cited_by_count":7}],"next_cursor":null}