Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion

Jie Li, Yow-Ting Shiue, Yong-Siang Shih, Jonas Geiping


Abstract
This paper describes our zero-shot approachesfor the Visual Word Sense Disambiguation(VWSD) Task in English. Our preliminarystudy shows that the simple approach of match-ing candidate images with the phrase usingCLIP suffers from the many-to-many natureof image-text pairs. We find that the CLIP textencoder may have limited abilities in captur-ing the compositionality in natural language. Conversely, the descriptive focus of the phrasevaries from instance to instance. We addressthese issues in our two systems, Augment-CLIPand Stable Diffusion Sampling (SD Sampling).Augment-CLIP augments the text prompt bygenerating sentences that contain the contextphrase with the help of large language mod-els (LLMs). We further explore CLIP modelsin other languages, as the an ambiguous wordmay be translated into an unambiguous one inthe other language. SD Sampling uses text-to-image Stable Diffusion to generate multipleimages from the given phrase, increasing thelikelihood that a subset of images match theone that paired with the text.
Anthology ID:
2023.semeval-1.5
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
44–49
Language:
URL:
https://aclanthology.org/2023.semeval-1.5
DOI:
10.18653/v1/2023.semeval-1.5
Bibkey:
Cite (ACL):
Jie Li, Yow-Ting Shiue, Yong-Siang Shih, and Jonas Geiping. 2023. Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 44–49, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion (Li et al., SemEval 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.semeval-1.5.pdf