Learning Functional Distributional Semantics with Visual Data

Yinhong Liu, Guy Emerson


Abstract
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In this work, we propose a method to train a Functional Distributional Semantics model with grounded visual data. We train it on the Visual Genome dataset, which is closer to the kind of data encountered in human language acquisition than a large text corpus. On four external evaluation datasets, our model outperforms previous work on learning semantics from Visual Genome.
Anthology ID:
2022.acl-long.275
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3976–3988
Language:
URL:
https://aclanthology.org/2022.acl-long.275
DOI:
10.18653/v1/2022.acl-long.275
Bibkey:
Cite (ACL):
Yinhong Liu and Guy Emerson. 2022. Learning Functional Distributional Semantics with Visual Data. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3976–3988, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Learning Functional Distributional Semantics with Visual Data (Liu & Emerson, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.275.pdf
Video:
 https://aclanthology.org/2022.acl-long.275.mp4
Data
Visual Question Answering