Skip-Thought Memory Networks

TL;DR

This paper introduces a novel approach combining end-to-end memory networks with Skip-Thought sentence vectors to improve question answering involving complex multi-entity relations.

Contribution

It presents a method that integrates Skip-Thought vectors into memory networks to better model multi-argument semantic relations for QA tasks.

Findings

Enhanced ability to answer questions with multiple entities

Improved modeling of multi-argument semantic relations

Effective integration of Skip-Thought vectors with memory networks

Abstract

Question Answering (QA) is fundamental to natural language processing in that most nlp problems can be phrased as QA (Kumar et al., 2015). Current weakly supervised memory network models that have been proposed so far struggle at answering questions that involve relations among multiple entities (such as facebook's bAbi qa5-three-arg-relations in (Weston et al., 2015)). To address this problem of learning multi-argument multi-hop semantic relations for the purpose of QA, we propose a method that combines the jointly learned long-term read-write memory and attentive inference components of end-to-end memory networks (MemN2N) (Sukhbaatar et al., 2015) with distributed sentence vector representations encoded by a Skip-Thought model (Kiros et al., 2015). This choice to append Skip-Thought Vectors to the existing MemN2N framework is motivated by the fact that Skip-Thought Vectors have been shown to accurately model multi-argument semantic relations (Kiros et al., 2015).