Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering

TL;DR

This paper introduces a neural network approach combining CNNs and LSTMs to improve answer selection in community question answering by modeling answer sequences for better matching quality assessment.

Contribution

It proposes a novel neural architecture that integrates CNNs and LSTMs for answer sequence labeling in CQA, enhancing answer matching accuracy.

Findings

Effective on SemEval 2015 CQA dataset

Outperforms traditional answer selection methods

Demonstrates the benefit of sequence modeling in answer ranking

Abstract

In this paper, the answer selection problem in community question answering (CQA) is regarded as an answer sequence labeling task, and a novel approach is proposed based on the recurrent architecture for this problem. Our approach applies convolution neural networks (CNNs) to learning the joint representation of question-answer pair firstly, and then uses the joint representation as input of the long short-term memory (LSTM) to learn the answer sequence of a question for labeling the matching quality of each answer. Experiments conducted on the SemEval 2015 CQA dataset shows the effectiveness of our approach.