Separating Answers from Queries for Neural Reading Comprehension

Abstract

We present a novel neural architecture for answering queries, designed to optimally leverage explicit support in the form of query-answer memories. Our model is able to refine and update a given query while separately accumulating evidence for predicting the answer. Its architecture reflects this separation with dedicated embedding matrices and loosely connected information pathways (modules) for updating the query and accumulating evidence. This separation of responsibilities effectively decouples the search for query related support and the prediction of the answer. On recent benchmark datasets for reading comprehension, our model achieves state-of-the-art results. A qualitative analysis reveals that the model effectively accumulates weighted evidence from the query and over multiple support retrieval cycles which results in a robust answer prediction.

References in corpus (1)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Cited by in corpus (4)

• Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
• Why can't memory networks read effectively?