Abstract
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.- Anthology ID:
- 2021.emnlp-main.140
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1852–1863
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.140
- DOI:
- 10.18653/v1/2021.emnlp-main.140
- Cite (ACL):
- Zeqiu Wu, Bo-Ru Lu, Hannaneh Hajishirzi, and Mari Ostendorf. 2021. DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1852–1863, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization (Wu et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/landing_page/2021.emnlp-main.140.pdf
- Code
- ellenmellon/dialki
- Data
- Doc2Dial, Holl-E, Wizard of Wikipedia, doc2dial