AlexU-AUX-BERT at SemEval-2020 Task 3: Improving BERT Contextual Similarity Using Multiple Auxiliary Contexts

Somaia Mahmoud, Marwan Torki


Abstract
This paper describes the system we built for SemEval-2020 task 3. That is predicting the scores of similarity for a pair of words within two different contexts. Our system is based on both BERT embeddings and WordNet. We simply use cosine similarity to find the closest synset of the target words. Our results show that using this simple approach greatly improves the system behavior. Our model is ranked 3rd in subtask-2 for SemEval-2020 task 3.
Anthology ID:
2020.semeval-1.33
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:
270–274
Language:
URL:
https://aclanthology.org/2020.semeval-1.33
DOI:
10.18653/v1/2020.semeval-1.33
Bibkey:
Cite (ACL):
Somaia Mahmoud and Marwan Torki. 2020. AlexU-AUX-BERT at SemEval-2020 Task 3: Improving BERT Contextual Similarity Using Multiple Auxiliary Contexts. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 270–274, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
AlexU-AUX-BERT at SemEval-2020 Task 3: Improving BERT Contextual Similarity Using Multiple Auxiliary Contexts (Mahmoud & Torki, SemEval 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2020.semeval-1.33.pdf