Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation

Wen Zheng, Natasa Milic-Frayling, Ke Zhou


Abstract
This paper is concerned with improving dialogue generation models through injection of knowledge, e.g., content relevant to the post that can increase the quality of responses. Past research extends the training of the generative models by incorporating statistical properties of posts, responses and related knowledge, without explicitly assessing the knowledge quality. In our work, we demonstrate the importance of knowledge relevance and adopt a two-phase approach. We first apply a novel method, Transformer & Post based Posterior Approximation (TPPA) to select knowledge, and then use the Transformer with Expanded Decoder (TED) model to generate responses from both the post and the knowledge. TPPA method processes posts, post related knowledge, and response related knowledge at both word and sentence level. Our experiments with the TED generative model demonstrate the effectiveness of TPPA as it outperforms a set of strong baseline models. Our TPPA method is extendable and supports further optimization of knowledge retrieval and injection.
Anthology ID:
2020.findings-emnlp.321
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3581–3591
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.321
DOI:
10.18653/v1/2020.findings-emnlp.321
Bibkey:
Cite (ACL):
Wen Zheng, Natasa Milic-Frayling, and Ke Zhou. 2020. Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3581–3591, Online. Association for Computational Linguistics.
Cite (Informal):
Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation (Zheng et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.321.pdf
Code
 tonywenuon/emnlp2020_tppa
Data
Holl-EWizard of Wikipedia