Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots

TL;DR

This paper introduces a novel response generation model for multi-party chatbots that incorporates interlocutor-aware contexts, improving response relevance by capturing complex interactions among multiple participants.

Contribution

The paper proposes ICRED, a new model that integrates interlocutor-aware representations and addressee memory for more accurate multi-party response generation.

Findings

ICRED outperforms strong baselines in automatic evaluations.

The model effectively captures dialogue context for different interlocutors.

A new corpus for RGMPC was constructed based on an existing dataset.

Abstract

Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene. In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors' roles (e.g., speaker and addressee) and their utterances. Unfortunately, complex interactions among the interlocutors' roles make it challenging to precisely capture conversational contexts and interlocutors' information. Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC. Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors. Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee. Finally, we construct a corpus for RGMPC based on an existing open-access dataset. Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.