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

Hansi Hettiarachchi, Tharindu Ranasinghe


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.
Anthology ID:
2021.semeval-1.102
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
771–779
Language:
URL:
https://aclanthology.org/2021.semeval-1.102
DOI:
10.18653/v1/2021.semeval-1.102
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.102.pdf
Data
WiC