Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning
This work addresses a specific NLP task for researchers, but it is incremental as it builds on existing fine-tuning techniques with a minor modification.
The paper tackled the problem of word-in-context disambiguation in the SemEval-2021 Task 2 by fine-tuning BERT models, achieving an accuracy of 92.7% with a method combining Cosine Similarity and ReLU activation.
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.