arXiv (Cornell University) · 2016 · 463 citations · 23 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingLanguage ModelsNatural Language UnderstandingNeural NetworksSentiment AnalysisErasure CorrectionEvaluation MetricsFeature ClassificationInterpretable Neural NetworksLinguistic Feature AnalysisNeural Language ModelsNeural Network InterpretabilityNeural Text Representation
While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural model by observing the effects on the model of erasing various parts of the representation, such as input word-vector dimensions, intermediate hidden units, or input words. We present several approaches to analyzing the effects of such erasure, from computing the relative difference in evaluation metrics, to using reinforcement learning to erase the minimum set of input words in order to flip a neural model's decision. In a comprehensive analysis of multiple NLP tasks, including linguistic feature classification, sentence-level sentiment analysis, and document level sentiment aspect prediction, we show that the proposed methodology not only offers clear explanations about neural model decisions, but also provides a way to conduct error analysis on neural models.
23
Efficient Estimation of Word Representations in Vector Space
Tomáš Mikolov, Kai Chen, Greg S. Corrado et al. · arXiv (Cornell University) · 2013 · 11.7K citations · Full text
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Jun‐Young Chung, Çağlar Gülçehre, Kyunghyun Cho et al. · arXiv (Cornell University) · 2014 · 10.8K citations · Full text
Klaus Greff, Rupesh K. Srivastava, Jan Koutník et al. · IEEE Transactions on Neural Networks and Learning Systems · 2016 · 6.8K citations · Full text
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text