Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size

Sandro Pezzelle, Raquel Fernández


Abstract
In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities – modeling the multimodal, contextually-dependent meaning of size adjectives (‘big’, ‘small’) – and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task.
Anthology ID:
D19-6403
Volume:
Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Aditya Mogadala, Dietrich Klakow, Sandro Pezzelle, Marie-Francine Moens
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18–23
Language:
URL:
https://aclanthology.org/D19-6403
DOI:
10.18653/v1/D19-6403
Bibkey:
Cite (ACL):
Sandro Pezzelle and Raquel Fernández. 2019. Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size. In Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN), pages 18–23, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size (Pezzelle & Fernández, 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6403.pdf