TransWiC at SemEval-2021 Task 2: Transformer-based Multilingual and Cross-lingual Word-in-Context Disambiguation

Hettiarachchi, Hansi and Ranasinghe, Tharindu (2021) TransWiC at SemEval-2021 Task 2: Transformer-based Multilingual and Cross-lingual Word-in-Context Disambiguation. In: 15th International Workshop on Semantic Evaluation (SemEval-2021), 1st August 2021, Online.

Preview

Text SemEval-2021-TransWiC at SemEval-2021 Task 2 Transformer-based Multilingual and Cross-lingual Word-in-Context Disambiguation.pdf - Published Version Available under License Creative Commons Attribution. Download (958kB)

Abstract

Identifying whether a word carries the same meaning or different meaning in two contexts is an important research area in natural language processing which plays a significant role in many applications such as question answering, document summarisation, information retrieval and information extraction. Most of the previous work in this area rely on language-specific resources making it difficult to generalise across languages. Considering this limitation, our approach to SemEval-2021 Task 2 is based only on pretrained transformer models and does not use any language-specific processing and resources. Despite that, our best model achieves 0.90 accuracy for English-English subtask which is very compatible compared to the best result of the subtask; 0.93 accuracy. Our approach also achieves satisfactory results in other monolingual and cross-lingual language pairs as well.

Item Type:	Conference or Workshop Item (Paper)
Identification Number:	10.18653/v1/2021.semeval-1.102
Dates:	Date Event 29 March 2021 Accepted 6 August 2021 Published
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Hansi Hettiarachchi
Date Deposited:	21 Dec 2021 15:50
Last Modified:	21 Dec 2021 15:50
URI:	https://www.open-access.bcu.ac.uk/id/eprint/12551

Actions (login required)

View Item