{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"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":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1808.09031","title":"Targeted Syntactic Evaluation of Language Models","created":"2018-08-27","cited_by_count":242},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"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":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1704.03471","title":"What do Neural Machine Translation Models Learn about Morphology?","created":"2017-04-11","cited_by_count":166},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1902.05622","title":"The Shapley Taylor Interaction Index","created":"2019-02-14","cited_by_count":143},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"2005.13407","title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","created":"2020-05-27","cited_by_count":117},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"1903.07435","title":"The emergence of number and syntax units in LSTM language models","created":"2019-03-18","cited_by_count":94},{"id":"1805.12233","title":"How Important Is a Neuron?","created":"2018-05-30","cited_by_count":73},{"id":"1801.05453","title":"Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs","created":"2018-01-16","cited_by_count":67},{"id":"2004.14992","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","created":"2020-04-30","cited_by_count":63},{"id":"1801.07772","title":"Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks","created":"2018-01-23","cited_by_count":56},{"id":"2005.01172","title":"Similarity Analysis of Contextual Word Representation Models","created":"2020-05-03","cited_by_count":54},{"id":"2010.02812","title":"Intrinsic Probing through Dimension Selection","created":"2020-10-06","cited_by_count":45},{"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":"1911.00317","title":"On the Linguistic Representational Power of Neural Machine Translation Models","created":"2019-11-01","cited_by_count":34},{"id":"2004.14513","title":"Asking without Telling: Exploring Latent Ontologies in Contextual Representations","created":"2020-04-29","cited_by_count":34},{"id":"2105.15179","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","created":"2021-05-31","cited_by_count":32},{"id":"2005.07647","title":"Finding Experts in Transformer Models","created":"2020-05-15","cited_by_count":28},{"id":"1902.07249","title":"Discovery of Natural Language Concepts in Individual Units of CNNs","created":"2019-02-18","cited_by_count":21},{"id":"1809.07291","title":"Interpretable Textual Neuron Representations for NLP","created":"2018-09-19","cited_by_count":16},{"id":"2103.13678","title":"Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation","created":"2021-03-25","cited_by_count":15},{"id":"1804.06679","title":"Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation","created":"2018-04-18","cited_by_count":13},{"id":"2004.01254","title":"Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations","created":"2020-04-02","cited_by_count":12},{"id":"2104.07456","title":"Effect of Post-processing on Contextualized Word Representations","created":"2021-04-15","cited_by_count":7},{"id":"1808.09551","title":"Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?","created":"2018-08-28","cited_by_count":5},{"id":"1912.05308","title":"Unsupervised Transfer Learning via BERT Neuron Selection","created":"2019-12-10","cited_by_count":4}],"next_cursor":null}