Papers › Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning

Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning

13 Apr 2021SEMEVAL 2021arXiv:2104.06439archive 2025-07-28

Boris Zhestiankin, Maria Ponomareva

This paper presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7%, which is the fourth-best score in EN-EN sub-track.

PaperPDFConference PDFCode

Code

zhestyatsky/MCL-WiC officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Task 2

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections