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

P. 780–786.

Davletov A., Nikolay Arefyev, Gordeev D., Rey A.

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.

Keywords: natural language processing, computational lexical semantics

Publication based on the results of: Development of Mathematical Models and Methods for Recommender Systems and Natural Language Processing (2020)

In book

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

Association for Computational Linguistics, 2021.