BabelEnconding at SemEval-2020 Task 3: Contextual Similarity as a Combination of Multilingualism and Language Models

Lucas Rafael Costella Pessutto, Tiago de Melo, Viviane P. Moreira, Altigran da Silva


Abstract
This paper describes the system submitted by our team (BabelEnconding) to SemEval-2020 Task 3: Predicting the Graded Effect of Context in Word Similarity. We propose an approach that relies on translation and multilingual language models in order to compute the contextual similarity between pairs of words. Our hypothesis is that evidence from additional languages can leverage the correlation with the human generated scores. BabelEnconding was applied to both subtasks and ranked among the top-3 in six out of eight task/language combinations and was the highest scoring system three times.
Anthology ID:
2020.semeval-1.5
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:
59–66
Language:
URL:
https://aclanthology.org/2020.semeval-1.5
DOI:
10.18653/v1/2020.semeval-1.5
Bibkey:
Cite (ACL):
Lucas Rafael Costella Pessutto, Tiago de Melo, Viviane P. Moreira, and Altigran da Silva. 2020. BabelEnconding at SemEval-2020 Task 3: Contextual Similarity as a Combination of Multilingualism and Language Models. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 59–66, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
BabelEnconding at SemEval-2020 Task 3: Contextual Similarity as a Combination of Multilingualism and Language Models (Costella Pessutto et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.5.pdf