SemEval-2023 Task 1: Visual Word Sense Disambiguation

Alessandro Raganato; Iacer Calixto; Asahi Ushio; Jose Camacho-Collados; Mohammad Taher Pilehvar

doi:https://doi.org/10.18653/v1/2023.semeval-1.308

SemEval-2023 Task 1: Visual Word Sense Disambiguation

Alessandro Raganato, Iacer Calixto, Asahi Ushio, Jose Camacho-Collados, Mohammad Taher Pilehvar

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

This paper presents the Visual Word Sense Disambiguation (Visual-WSD) task. The objective of Visual-WSD is to identify among a set of ten images the one that corresponds to the intended meaning of a given ambiguous word which is accompanied with minimal context. The task provides datasets for three different languages: English, Italian, and Farsi.We received a total of 96 different submissions. Out of these, 40 systems outperformed a strong zero-shot CLIP-based baseline. Participating systems proposed different zero- and few-shot approaches, often involving generative models and data augmentation. More information can be found on the task's website: textbackslashurlhttps://raganato.github.io/vwsd/.

Original language	English
Title of host publication	Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Place of Publication	Toronto, Canada
Publisher	Association for Computational Linguistics (ACL)
Pages	2227-2234
Number of pages	8
DOIs	https://doi.org/10.18653/v1/2023.semeval-1.308
Publication status	Published - 1 Jul 2023

Access to Document

https://doi.org/10.18653/v1/2023.semeval-1.308

https://aclanthology.org/2023.semeval-1.308

Cite this

@inproceedings{e2f8d51f63454db28b1a407715af7631,

title = "SemEval-2023 Task 1: Visual Word Sense Disambiguation",

abstract = "This paper presents the Visual Word Sense Disambiguation (Visual-WSD) task. The objective of Visual-WSD is to identify among a set of ten images the one that corresponds to the intended meaning of a given ambiguous word which is accompanied with minimal context. The task provides datasets for three different languages: English, Italian, and Farsi.We received a total of 96 different submissions. Out of these, 40 systems outperformed a strong zero-shot CLIP-based baseline. Participating systems proposed different zero- and few-shot approaches, often involving generative models and data augmentation. More information can be found on the task's website: textbackslashurlhttps://raganato.github.io/vwsd/.",

author = "Alessandro Raganato and Iacer Calixto and Asahi Ushio and Jose Camacho-Collados and Pilehvar, {Mohammad Taher}",

year = "2023",

month = jul,

day = "1",

doi = "https://doi.org/10.18653/v1/2023.semeval-1.308",

language = "English",

pages = "2227--2234",

booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",

publisher = "Association for Computational Linguistics (ACL)",

}

SemEval-2023 Task 1: Visual Word Sense Disambiguation. / Raganato, Alessandro; Calixto, Iacer; Ushio, Asahi et al.
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023). Toronto, Canada: Association for Computational Linguistics (ACL), 2023. p. 2227-2234.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - SemEval-2023 Task 1: Visual Word Sense Disambiguation

AU - Raganato, Alessandro

AU - Calixto, Iacer

AU - Ushio, Asahi

AU - Camacho-Collados, Jose

AU - Pilehvar, Mohammad Taher

PY - 2023/7/1

Y1 - 2023/7/1

N2 - This paper presents the Visual Word Sense Disambiguation (Visual-WSD) task. The objective of Visual-WSD is to identify among a set of ten images the one that corresponds to the intended meaning of a given ambiguous word which is accompanied with minimal context. The task provides datasets for three different languages: English, Italian, and Farsi.We received a total of 96 different submissions. Out of these, 40 systems outperformed a strong zero-shot CLIP-based baseline. Participating systems proposed different zero- and few-shot approaches, often involving generative models and data augmentation. More information can be found on the task's website: textbackslashurlhttps://raganato.github.io/vwsd/.

AB - This paper presents the Visual Word Sense Disambiguation (Visual-WSD) task. The objective of Visual-WSD is to identify among a set of ten images the one that corresponds to the intended meaning of a given ambiguous word which is accompanied with minimal context. The task provides datasets for three different languages: English, Italian, and Farsi.We received a total of 96 different submissions. Out of these, 40 systems outperformed a strong zero-shot CLIP-based baseline. Participating systems proposed different zero- and few-shot approaches, often involving generative models and data augmentation. More information can be found on the task's website: textbackslashurlhttps://raganato.github.io/vwsd/.

U2 - https://doi.org/10.18653/v1/2023.semeval-1.308

DO - https://doi.org/10.18653/v1/2023.semeval-1.308

M3 - Conference contribution

SP - 2227

EP - 2234

BT - Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

PB - Association for Computational Linguistics (ACL)

CY - Toronto, Canada

ER -