Conversational Semantic Parsing for Dialog State Tracking
Jianpeng Cheng, Devang Agrawal, Héctor Martínez Alonso, Shruti Bhargava, Joris Driesen, Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D. Williams, Hong Yu, Diarmuid Ó Séaghdha, Anders Johannsen
Abstract
We consider a new perspective on dialog state tracking (DST), the task of estimating a user’s goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to ~20% improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.- Anthology ID:
- 2020.emnlp-main.651
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8107–8117
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.651
- DOI:
- 10.18653/v1/2020.emnlp-main.651
- Cite (ACL):
- Jianpeng Cheng, Devang Agrawal, Héctor Martínez Alonso, Shruti Bhargava, Joris Driesen, Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D. Williams, Hong Yu, Diarmuid Ó Séaghdha, and Anders Johannsen. 2020. Conversational Semantic Parsing for Dialog State Tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8107–8117, Online. Association for Computational Linguistics.
- Cite (Informal):
- Conversational Semantic Parsing for Dialog State Tracking (Cheng et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.emnlp-main.651.pdf
- Code
- apple/ml-tree-dst
- Data
- SGD