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

Martin Pömsl, Roman Lyapin


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.
Anthology ID:
2020.semeval-1.21
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Editors:
Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
Venue:
SemEval
SIG:
SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
180–186
Language:
URL:
https://aclanthology.org/2020.semeval-1.21
DOI:
10.18653/v1/2020.semeval-1.21
Bibkey:
Cite (ACL):
Martin Pömsl and Roman Lyapin. 2020. CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 180–186, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations (Pömsl & Lyapin, SemEval 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.semeval-1.21.pdf
Code
 mpoemsl/circe +  additional community code