Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations

Wessel Poelman, Rik van Noord, Johan Bos


Abstract
Even though many recent semantic parsers are based on deep learning methods, we should not forget that rule-based alternatives might offer advantages over neural approaches with respect to transparency, portability, and explainability. Taking advantage of existing off-the-shelf Universal Dependency parsers, we present a method that maps a syntactic dependency tree to a formal meaning representation based on Discourse Representation Theory. Rather than using lambda calculus to manage variable bindings, our approach is novel in that it consists of using a series of graph transformations. The resulting UD semantic parser shows good performance for English, German, Italian and Dutch, with F-scores over 75%, outperforming a neural semantic parser for the lower-resourced languages. Unlike neural semantic parsers, our UD semantic parser does not hallucinate output, is relatively easy to port to other languages, and is completely transparent.
Anthology ID:
2022.coling-1.367
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4186–4192
Language:
URL:
https://aclanthology.org/2022.coling-1.367
DOI:
Bibkey:
Cite (ACL):
Wessel Poelman, Rik van Noord, and Johan Bos. 2022. Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4186–4192, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (Poelman et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2022.coling-1.367.pdf
Code
 wpoelman/ud-boxer