Abstract
Knowledge-grounded dialogue is a task of gener- ating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manu- ally annotated knowledge graphs and knowledge text from website. From various evaluation viewpoints, each type of knowledge has advantages and downsides. To further distinguish the principles and determinants from the intricate factors, we conduct a thorough experiment and study on the task to answer three essential questions. The ques- tions involve the choice of appropriate knowledge form, the degree of mutual effects between knowl- edge and the model selection, and the few-shot performance of knowledge. Supported by statistical shreds of evidence, we offer conclusive solutions and sensible suggestions for directions and standards of future research.- Anthology ID:
- 2023.emnlp-main.982
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 15846–15858
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.982
- DOI:
- 10.18653/v1/2023.emnlp-main.982
- Cite (ACL):
- Yizhe Yang, Heyan Huang, Yuhang Liu, and Yang Gao. 2023. Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15846–15858, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue (Yang et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.982.pdf