DEMN: Distilled-Exposition Enhanced Matching Network for Story Comprehension

TL;DR

This paper introduces DEMN, a novel neural network model that enhances story comprehension by distilling exposition information to improve story ending prediction, achieving state-of-the-art accuracy on ROCStories.

Contribution

The paper presents a new model that explicitly incorporates exposition distillation into story matching, advancing story understanding techniques.

Findings

Achieved 80.1% accuracy on ROCStories test set.

Demonstrated state-of-the-art performance in story comprehension.

Effective integration of exposition distillation improves prediction accuracy.

Abstract

This paper proposes a Distilled-Exposition Enhanced Matching Network (DEMN) for story-cloze test, which is still a challenging task in story comprehension. We divide a complete story into three narrative segments: an \textit{exposition}, a \textit{climax}, and an \textit{ending}. The model consists of three modules: input module, matching module, and distillation module. The input module provides semantic representations for the three segments and then feeds them into the other two modules. The matching module collects interaction features between the ending and the climax. The distillation module distills the crucial semantic information in the exposition and infuses it into the matching module in two different ways. We evaluate our single and ensemble model on ROCStories Corpus \cite{Mostafazadeh2016ACA}, achieving an accuracy of 80.1\% and 81.2\% on the test set respectively. The experimental results demonstrate that our DEMN model achieves a state-of-the-art performance.