Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur
Abstract
Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present Think-Before-Speaking (TBS), a generative approach to first externalize implicit commonsense knowledge (think) and use this knowledge to generate responses (speak). We argue that externalizing implicit knowledge allows more efficient learning, produces more informative responses, and enables more explainable models. We analyze different choices to collect knowledge-aligned dialogues, represent implicit knowledge, and transition between knowledge and dialogues. Empirical results show TBS models outperform end-to-end and knowledge-augmented RG baselines on most automatic metrics and generate more informative, specific, and commonsense-following responses, as evaluated by human annotators. TBS also generates knowledge that makes sense and is relevant to the dialogue around 85% of the time
BibTeX
@inproceedings{zhou-etal-2022-think,
title = "Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation",
author = "Zhou, Pei and
Gopalakrishnan, Karthik and
Hedayatnia, Behnam and
Kim, Seokhwan and
Pujara, Jay and
Ren, Xiang and
Liu, Yang and
Hakkani-Tur, Dilek",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.88/",
doi = "10.18653/v1/2022.acl-long.88",
pages = "1237--1252"
}