Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots

TL;DR

This paper introduces S2M, a sequential sentence matching network that leverages sentence-level semantics for improved multi-turn response selection in retrieval-based chatbots, achieving state-of-the-art results.

Contribution

The paper proposes a novel sentence-level semantic matching network (S2M) that enhances multi-turn response selection and combines it with word similarity matching for better performance.

Findings

S2M significantly outperforms previous models.

Integrating sentence-level and word-level matching improves results.

Achieves state-of-the-art performance on three datasets.

Abstract

Recently, open domain multi-turn chatbots have attracted much interest from lots of researchers in both academia and industry. The dominant retrieval-based methods use context-response matching mechanisms for multi-turn response selection. Specifically, the state-of-the-art methods perform the context-response matching by word or segment similarity. However, these models lack a full exploitation of the sentence-level semantic information, and make simple mistakes that humans can easily avoid. In this work, we propose a matching network, called sequential sentence matching network (S2M), to use the sentence-level semantic information to address the problem. Firstly and most importantly, we find that by using the sentence-level semantic information, the network successfully addresses the problem and gets a significant improvement on matching, resulting in a state-of-the-art performance. Furthermore, we integrate the sentence matching we introduced here and the usual word similarity matching reported in the current literature, to match at different semantic levels. Experiments on three public data sets show that such integration further improves the model performance.