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.
@article{arxiv.2005.06602,
title = {CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations},
author = {Martin Pömsl and Roman Lyapin},
journal= {arXiv preprint arXiv:2005.06602},
year = {2020}
}
Comments
Accepted at SemEval-2020 Task 1 @ COLING 2020. Code available at https://github.com/mpoemsl/circe