How recurrent networks implement contextual processing in sentiment analysis

Abstract

Neural networks have a remarkable capacity for contextual processing--using recent or nearby inputs to modify processing of current input. For example, in natural language, contextual processing is necessary to correctly interpret negation (e.g. phrases such as "not bad"). However, our ability to understand how networks process context is limited. Here, we propose general methods for reverse engineering recurrent neural networks (RNNs) to identify and elucidate contextual processing. We apply these methods to understand RNNs trained on sentiment classification. This analysis reveals inputs that induce contextual effects, quantifies the strength and timescale of these effects, and identifies sets of these inputs with similar properties. Additionally, we analyze contextual effects related to differential processing of the beginning and end of documents. Using the insights learned from the RNNs we improve baseline Bag-of-Words models with simple extensions that incorporate contextual modification, recovering greater than 90% of the RNN's performance increase over the baseline. This work yields a new understanding of how RNNs process contextual information, and provides tools that should provide similar insight more broadly.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Visualizing and Understanding Recurrent Networks
• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
• Visualizing and Understanding Neural Models in NLP
• Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
• Linguistically Regularized LSTMs for Sentiment Classification
• An Empirical Analysis of the Role of Amplifiers, Downtoners, and Negations in Emotion Classification in Microblogs

Cited by in corpus (6)

• Meta-trained agents implement Bayes-optimal agents
• Auxiliary Tasks and Exploration Enable ObjectNav
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
• Understanding How Encoder-Decoder Architectures Attend
• The geometry of integration in text classification RNNs
• Reverse engineering learned optimizers reveals known and novel mechanisms