Abstract
In this paper we consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types. We focus on models which are capable of interactively mapping user utterances into executable logical forms (e.g., Sparql) in the context of the conversational history. Our key idea is to represent information about an utterance and its context via a subgraph which is created dynamically, i.e., the number of nodes varies per utterance. Rather than treating the subgraph as a sequence, we exploit its underlying structure and encode it with a graph neural network which further allows us to represent a large number of (unseen) nodes. Experimental results show that dynamic context modeling is superior to static approaches, delivering performance improvements across the board (i.e., for simple and complex questions). Our results further confirm that modeling the structure of context is better at processing discourse information, (i.e., at handling ellipsis and resolving coreference) and longer interactions.- Anthology ID:
- 2023.emnlp-main.535
- 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:
- 8667–8679
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.535
- DOI:
- 10.18653/v1/2023.emnlp-main.535
- Cite (ACL):
- Parag Jain and Mirella Lapata. 2023. Conversational Semantic Parsing using Dynamic Context Graphs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8667–8679, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Conversational Semantic Parsing using Dynamic Context Graphs (Jain & Lapata, EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.535.pdf