Abstract
In this paper we present a novel application of compositional distributional semantic models (CDSMs): prediction of lexical typology. The paper introduces the notion of typological closeness, which is a novel rigorous formalization of semantic similarity based on comparison of multilingual data. Starting from the Moscow Database of Qualitative Features for adjective typology, we create four datasets of typological closeness, on which we test a range of distributional semantic models. We show that, on the one hand, vector representations of phrases based on data from one language can be used to predict how words within the phrase translate into different languages, and, on the other hand, that typological data can serve as a semantic benchmark for distributional models. We find that compositional distributional models, especially parametric ones, perform way above non-compositional alternatives on the task.- Anthology ID:
- L16-1199
- Volume:
- Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
- Month:
- May
- Year:
- 2016
- Address:
- Portorož, Slovenia
- Editors:
- Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 1253–1257
- Language:
- URL:
- https://aclanthology.org/L16-1199
- DOI:
- Cite (ACL):
- Daria Ryzhova, Maria Kyuseva, and Denis Paperno. 2016. Typology of Adjectives Benchmark for Compositional Distributional Models. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1253–1257, Portorož, Slovenia. European Language Resources Association (ELRA).
- Cite (Informal):
- Typology of Adjectives Benchmark for Compositional Distributional Models (Ryzhova et al., LREC 2016)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/L16-1199.pdf