Nothing Special   »   [go: up one dir, main page]

Combining Tradition with Modernness: Exploring Event Representations in Vision-and-Language Models for Visual Goal-Step Inference

Chong Shen, Carina Silberer


Abstract
Procedural knowledge understanding (PKU) underlies the ability to infer goal-step relations. The task of Visual Goal–Step Inference addresses this ability in the multimodal domain. It requires to identify images that represent the steps towards achieving a textually expressed goal. The best existing methods encode texts and images either with independent encoders, or with object-level multimodal encoders using blackbox transformers. This stands in contrast to early, linguistically inspired methods for event representations, which focus on capturing the most crucial information, namely actions and the participants, to learn stereotypical event sequences and hence procedural knowledge. In this work, we study various methods and their effects on PKU of injecting the early shallow event representations to nowadays multimodal deep learning-based models. We find that the early, linguistically inspired methods for representing event knowledge does contribute to understand procedures in combination with modern vision-and-language models. In the future, we are going to explore more complex structure of events and study how to exploit it on top of large language models.
Anthology ID:
2023.acl-srw.36
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Vishakh Padmakumar, Gisela Vallejo, Yao Fu
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
254–265
Language:
URL:
https://aclanthology.org/2023.acl-srw.36
DOI:
10.18653/v1/2023.acl-srw.36
Bibkey:
Cite (ACL):
Chong Shen and Carina Silberer. 2023. Combining Tradition with Modernness: Exploring Event Representations in Vision-and-Language Models for Visual Goal-Step Inference. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 254–265, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Combining Tradition with Modernness: Exploring Event Representations in Vision-and-Language Models for Visual Goal-Step Inference (Shen & Silberer, ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-srw.36.pdf
Video:
 https://aclanthology.org/2023.acl-srw.36.mp4