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 (Radford et al., 2021). 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: https://raganato.github.io/vwsd/.
Raganato, A., Calixto, I., Ushio, A., Camacho-Collados, J., Pilehvar, M. (2023). SemEval-2023 Task 1: Visual Word Sense Disambiguation. In 17th International Workshop on Semantic Evaluation, SemEval 2023 - Proceedings of the Workshop (pp.2227-2234). Association for Computational Linguistics [10.18653/v1/2023.semeval-1.308].
SemEval-2023 Task 1: Visual Word Sense Disambiguation
Raganato A.
;
2023
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 (Radford et al., 2021). 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: https://raganato.github.io/vwsd/.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Raganato-2023-SemEval-VoR.pdf
accesso aperto
Descrizione: Intervento a convegno
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Creative Commons
Dimensione
4.82 MB
Formato
Adobe PDF
|
4.82 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
