Exploring the Effectiveness of Multi-Lingual Commonsense Knowledge-Aware Open-Domain Dialogue Response Generation

Sixing Wu, Jiong Yu, Tianshi Che, Yang Zhou, Wei Zhou


Abstract
Prior works have shown the promising results of commonsense knowledge-aware models in improving informativeness while reducing the hallucination issue. Nonetheless, prior works often can only use monolingual knowledge whose language is consistent with the dialogue context. Except for a few high-resource languages, such as English and Chinese, most languages suffer from insufficient knowledge issues, especially minority languages. To this end, this work proposes a new task, Multi-Lingual Commonsense Knowledge-Aware Response Generation (MCKRG), which tries to use commonsense knowledge in other languages to enhance the current dialogue generation. Then, we construct a MCKRG dataset MCK-Dialog of seven languages with multiple alignment methods. Finally, we verify the effectiveness of using multi-lingual commonsense knowledge with a proposed MCK-T5 model. Extensive experimental results demonstrate the great potential of using multi-lingual commonsense knowledge in high-resource and low-resource languages. To the best of our knowledge, this work is the first to explore Multi-Lingual Commonsense Knowledge-Aware Response Generation.
Anthology ID:
2023.findings-emnlp.987
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14804–14814
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.987
DOI:
10.18653/v1/2023.findings-emnlp.987
Bibkey:
Cite (ACL):
Sixing Wu, Jiong Yu, Tianshi Che, Yang Zhou, and Wei Zhou. 2023. Exploring the Effectiveness of Multi-Lingual Commonsense Knowledge-Aware Open-Domain Dialogue Response Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14804–14814, Singapore. Association for Computational Linguistics.
Cite (Informal):
Exploring the Effectiveness of Multi-Lingual Commonsense Knowledge-Aware Open-Domain Dialogue Response Generation (Wu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.987.pdf