Abstract
Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to classify each candidate snippet as “relevant” or “irrelevant” independently. However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets. Moreover, they lack modeling of the discourse structure of dialogue-knowledge interactions. We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. GenKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogue-knowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.- Anthology ID:
- 2023.findings-eacl.155
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2077–2088
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.155
- DOI:
- 10.18653/v1/2023.findings-eacl.155
- Cite (ACL):
- Weiwei Sun, Pengjie Ren, and Zhaochun Ren. 2023. Generative Knowledge Selection for Knowledge-Grounded Dialogues. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2077–2088, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Generative Knowledge Selection for Knowledge-Grounded Dialogues (Sun et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-eacl.155.pdf