Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG

Alain Vazquez Risco, Angela Maria Ramirez, Neha Pullabhotla, Nan Qiang, Haoran Zhang, Marilyn Walker, Maria Ines Torres


Abstract
Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We aim to create an NLG engine that can produce a variety of DAs that make substantive knowledge-grounded contributions to a conversation. Training such an NLG typically requires dialogue corpora that are labelled for DAs, which are expensive to produce and vulnerable to quality issues. Here, we present a prompt-based learning approach to transfer DAs from one domain, video games, to 7 new domains. For each novel domain, we first crawl WikiData to create Meaning Representations that systematically vary both the number of attributes and hops on the WikiData Knowledge Graph. The proposed method involves a self-training step to create prompt examples for each domain followed by an overgeneration and ranking step. The result is a novel, high-quality dataset, Wiki-Dialogue, of 71K knowledge-grounded utterances, covering 9 DAs and the Art, Movies, Music, Sports, TV, Animal, and Boardgames domains, whose combined DA and semantic accuracy is 89%. We assess the corpus quality using both automatic and human evaluations and find it high. The corpus is found to be safe, lexically rich, and large in vocabulary, when compared to similar datasets.
Anthology ID:
2024.sigdial-1.7
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–91
Language:
URL:
https://aclanthology.org/2024.sigdial-1.7
DOI:
10.18653/v1/2024.sigdial-1.7
Bibkey:
Cite (ACL):
Alain Vazquez Risco, Angela Maria Ramirez, Neha Pullabhotla, Nan Qiang, Haoran Zhang, Marilyn Walker, and Maria Ines Torres. 2024. Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 78–91, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG (Vazquez Risco et al., SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.7.pdf