Abstract
The syntactic categories of categorial grammar formalisms are structured units made of smaller, indivisible primitives, bound together by the underlying grammar’s category formation rules. In the trending approach of constructive supertagging, neural models are increasingly made aware of the internal category structure. In turn, this enables them to more reliably predict rare and out-of-vocabulary categories. with significant implications for grammars previously deemed too complex to find practical use. In this work, we revisit constructive supertagging from a graph-theoretic perspective, and propose a framework based on heterogeneous dynamic graph convolutions, aimed at exploiting the distinctive structure of a supertagger’s output space. We test our approach on a number of categorial grammar datasets spanning different languages and grammar formalisms, achieving substantial improvements over previous state of the art scores.- Anthology ID:
- 2023.clasp-1.13
- Volume:
- Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)
- Month:
- September
- Year:
- 2023
- Address:
- Gothenburg, Sweden
- Editors:
- Ellen Breitholtz, Shalom Lappin, Sharid Loaiciga, Nikolai Ilinykh, Simon Dobnik
- Venue:
- CLASP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 107–119
- Language:
- URL:
- https://aclanthology.org/2023.clasp-1.13
- DOI:
- Cite (ACL):
- Konstantinos Kogkalidis and Michael Moortgat. 2023. Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions. In Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD), pages 107–119, Gothenburg, Sweden. Association for Computational Linguistics.
- Cite (Informal):
- Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions (Kogkalidis & Moortgat, CLASP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.clasp-1.13.pdf