Multilingual Supervision Improves Semantic Disambiguation of Adpositions

Wesley Scivetti, Lauren Levine, Nathan Schneider


Abstract
Adpositions display a remarkable amount of ambiguity and flexibility in their meanings, and are used in different ways across languages. We conduct a systematic corpus-based cross-linguistic investigation into the lexical semantics of adpositions, utilizing SNACS (Schneider et al., 2018), an annotation framework with data available in several languages. Our investigation encompasses 5 of these languages: Chinese, English, Gujarati, Hindi, and Japanese. We find substantial distributional differences in adposition semantics, even in comparable corpora. We further train classifiers to disambiguate adpositions in each of our languages. Despite the cross-linguistic differences in adpositional usage, sharing annotated data across languages boosts overall disambiguation performance, leading to the highest published scores on this task for all 5 languages.
Anthology ID:
2025.coling-main.247
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3655–3669
Language:
URL:
https://aclanthology.org/2025.coling-main.247/
DOI:
Bibkey:
Cite (ACL):
Wesley Scivetti, Lauren Levine, and Nathan Schneider. 2025. Multilingual Supervision Improves Semantic Disambiguation of Adpositions. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3655–3669, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Multilingual Supervision Improves Semantic Disambiguation of Adpositions (Scivetti et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.247.pdf