BRUMS at SemEval-2020 Task 3: Contextualised Embeddings for Predicting the (Graded) Effect of Context in Word Similarity
This work addresses a specific NLP benchmark task, showing incremental improvements in performance for language processing applications.
The paper tackled the problem of predicting graded word similarity in context across multiple languages by using contextualized word embeddings with task-specific adaptations, achieving top-5 rankings in all languages and first place in the Finnish subtask.
This paper presents the team BRUMS submission to SemEval-2020 Task 3: Graded Word Similarity in Context. The system utilises state-of-the-art contextualised word embeddings, which have some task-specific adaptations, including stacked embeddings and average embeddings. Overall, the approach achieves good evaluation scores across all the languages, while maintaining simplicity. Following the final rankings, our approach is ranked within the top 5 solutions of each language while preserving the 1st position of Finnish subtask 2.