LIORI at SemEval-2021 Task 2: Span Prediction and Binary Classification approaches to Word-in-Context Disambiguation

Adis Davletov, Nikolay Arefyev, Denis Gordeev, Alexey Rey


Abstract
This paper presents our approaches to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation task. The first approach attempted to reformulate the task as a question answering problem, while the second one framed it as a binary classification problem. Our best system, which is an ensemble of XLM-R based binary classifiers trained with data augmentation, is among the 3 best-performing systems for Russian, French and Arabic in the multilingual subtask. In the post-evaluation period, we experimented with batch normalization, subword pooling and target word occurrence aggregation methods, resulting in further performance improvements.
Anthology ID:
2021.semeval-1.103
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:
780–786
Language:
URL:
https://aclanthology.org/2021.semeval-1.103
DOI:
10.18653/v1/2021.semeval-1.103
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.103.pdf