CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations

Code

• github.com/mpoemsl/circe
  OfficialIn paperpytorch★ 3
• github.com/obj2vec/obj2vec
  none★ 0

Abstract

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.

Tasks

Reproductions