Automatic Rule Extraction from Long Short Term Memory Networks

2017/02/08 by Murdoch, W. James, Szlam, Arthur
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1702.02540

Abstract

Although deep learning models have proven effective at solving problems in natural language processing, the mechanism by which they come to their conclusions is often unclear. As a result, these models are generally treated as black boxes, yielding no insight of the underlying learned patterns. In this paper we consider Long Short Term Memory networks (LSTMs) and demonstrate a new approach for tracking the importance of a given input to the LSTM for a given output. By identifying consistently important patterns of words, we are able to distill state of the art LSTMs on sentiment analysis and question answering into a set of representative phrases. This representation is then quantitatively validated by using the extracted phrases to construct a simple, rule-based classifier which approximates the output of the LSTM.

Related

• Improved Semantic Representations From Tree-Structured Long Short-Term\n Memory Networks
• Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
• Knowledge extraction from the learning of sequences in a long short term memory (LSTM) architecture
• Learning Natural Language Inference with LSTM
• Effective LSTMs for Target-Dependent Sentiment Classification