Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering

TL;DR

This paper introduces a hierarchical gated recurrent neural tensor network for answer triggering, significantly improving the accuracy of identifying correct answers in question answering systems.

Contribution

The paper proposes a novel HGRNT model that captures context and deep answer-question interactions, advancing answer triggering performance.

Findings

Achieved 42.6% F-value on answer triggering task

Surpassed baseline performance by over 10%

Demonstrated effectiveness of hierarchical neural tensor network

Abstract

In this paper, we focus on the problem of answer triggering ad-dressed by Yang et al. (2015), which is a critical component for a real-world question answering system. We employ a hierarchical gated recurrent neural tensor (HGRNT) model to capture both the context information and the deep in-teractions between the candidate answers and the question. Our result on F val-ue achieves 42.6%, which surpasses the baseline by over 10 %.