Abstract
In this paper, we introduce our submission in the task of visual word sense disambiguation (vWSD). Our proposed solution operates by deriving quasi-symbolic semantic categories from the hidden representations of multi-modal text-image encoders. Our results are mixed, as we manage to achieve a substantial boost in performance when evaluating on a validation set, however, we experienced detrimental effects during evaluation on the actual test set. Our positive results on the validation set confirms the validity of the quasi-symbolic features, whereas our results on the test set revealed that the proposed technique was not able to cope with the sufficiently different distribution of the test data.- Anthology ID:
- 2023.semeval-1.270
- 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:
- 1965–1971
- Language:
- URL:
- https://aclanthology.org/2023.semeval-1.270
- DOI:
- 10.18653/v1/2023.semeval-1.270
- Cite (ACL):
- Gábor Berend. 2023. SzegedAI at SemEval-2023 Task 1: Applying Quasi-Symbolic Representations in Visual Word Sense Disambiguation. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1965–1971, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- SzegedAI at SemEval-2023 Task 1: Applying Quasi-Symbolic Representations in Visual Word Sense Disambiguation (Berend, SemEval 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.semeval-1.270.pdf