Abstract
Recent work in compositional distributional semantics showed how bialgebras model generalised quantifiers of natural language. That technique requires working with vector space over power sets of bases, and therefore is computationally costly. It is possible to overcome the computational hurdles by working with fuzzy generalised quantifiers. In this paper, we show that the compositional notion of semantics of natural language, guided by a grammar, extends from a binary to a many valued setting and instantiate in it the fuzzy computations. We import vector representations of words and predicates, learnt from large scale compositional distributional semantics, interpret them as fuzzy sets, and analyse their performance on a toy inference dataset.- Anthology ID:
- 2020.pam-1.12
- Volume:
- Proceedings of the Probability and Meaning Conference (PaM 2020)
- Month:
- June
- Year:
- 2020
- Address:
- Gothenburg
- Editors:
- Christine Howes, Stergios Chatzikyriakidis, Adam Ek, Vidya Somashekarappa
- Venue:
- PaM
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 86–94
- Language:
- URL:
- https://aclanthology.org/2020.pam-1.12
- DOI:
- Cite (ACL):
- Mehrnoosh Sadrzadeh and Gijs Wijnholds. 2020. A toy distributional model for fuzzy generalised quantifiers. In Proceedings of the Probability and Meaning Conference (PaM 2020), pages 86–94, Gothenburg. Association for Computational Linguistics.
- Cite (Informal):
- A toy distributional model for fuzzy generalised quantifiers (Sadrzadeh & Wijnholds, PaM 2020)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2020.pam-1.12.pdf