Natural Language Comprehension with the EpiReader

TL;DR

The EpiReader is a neural model that improves machine comprehension by proposing candidate answers and reranking hypotheses, achieving state-of-the-art results on major benchmarks.

Contribution

It introduces an end-to-end neural architecture with candidate proposal and hypothesis reranking components for improved comprehension.

Findings

Sets new state-of-the-art on CNN and Children's Book Test benchmarks.

Outperforms previous neural models significantly.

Demonstrates effectiveness of candidate proposal and reranking approach.

Abstract

We present the EpiReader, a novel model for machine comprehension of text. Machine comprehension of unstructured, real-world text is a major research goal for natural language processing. Current tests of machine comprehension pose questions whose answers can be inferred from some supporting text, and evaluate a model's response to the questions. The EpiReader is an end-to-end neural model comprising two components: the first component proposes a small set of candidate answers after comparing a question to its supporting text, and the second component formulates hypotheses using the proposed candidates and the question, then reranks the hypotheses based on their estimated concordance with the supporting text. We present experiments demonstrating that the EpiReader sets a new state-of-the-art on the CNN and Children's Book Test machine comprehension benchmarks, outperforming previous neural models by a significant margin.