Scope-enhanced Compositional Semantic Parsing for DRT

Xiulin Yang, Jonas Groschwitz, Alexander Koller, Johan Bos


Abstract
Discourse Representation Theory (DRT) distinguishes itself from other semantic representation frameworks by its ability to model complex semantic and discourse phenomena through structural nesting and variable binding. While seq2seq models hold the state of the art on DRT parsing, their accuracy degrades with the complexity of the sentence, and they sometimes struggle to produce well-formed DRT representations. We introduce the AMS parser, a compositional, neurosymbolic semantic parser for DRT. It rests on a novel mechanism for predicting quantifier scope. We show that the AMS parser reliably produces well-formed outputs and performs well on DRT parsing, especially on complex sentences.
Anthology ID:
2024.emnlp-main.1093
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19602–19616
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1093
DOI:
Bibkey:
Cite (ACL):
Xiulin Yang, Jonas Groschwitz, Alexander Koller, and Johan Bos. 2024. Scope-enhanced Compositional Semantic Parsing for DRT. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19602–19616, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Scope-enhanced Compositional Semantic Parsing for DRT (Yang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1093.pdf
Data:
 2024.emnlp-main.1093.data.zip