CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations
This work addresses lexical semantic change detection for computational linguistics, but it is incremental as it combines existing representation types.
The paper tackled unsupervised lexical semantic change detection by ensembling context-free and context-dependent word representations, achieving winning results in SemEval-2020 Task 1 with performance improvements on some datasets but decreases on others.
This paper describes the winning contribution to SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection (Subtask 2) handed in by team UG Student Intern. We present an ensemble model that makes predictions based on context-free and context-dependent word representations. The key findings are that (1) context-free word representations are a powerful and robust baseline, (2) a sentence classification objective can be used to obtain useful context-dependent word representations, and (3) combining those representations increases performance on some datasets while decreasing performance on others.