BRUMS at SemEval-2020 Task 3: Contextualised Embeddings for Predicting the (Graded) Effect of Context in Word Similarity

TL;DR

This paper introduces a system using contextualised embeddings for predicting graded word similarity in context, achieving top rankings across multiple languages with a simple yet effective approach.

Contribution

It applies state-of-the-art contextualised embeddings with task-specific adaptations to improve graded word similarity prediction in multilingual settings.

Findings

Top 5 ranking in all languages

First position in Finnish subtask 2

Effective use of stacked and average embeddings

Abstract

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.