MineriaUNAM at SemEval-2020 Task 3: Predicting Contextual WordSimilarity Using a Centroid Based Approach and Word Embeddings

Helena Gomez-Adorno, Gemma Bel-Enguix, Jorge Reyes-Magaña, Benjamín Moreno, Ramón Casillas, Daniel Vargas


Abstract
This paper presents our systems to solve Task 3 of Semeval-2020, which aims to predict the effect that context has on human perception of similarity of words. The task consists of two subtasks in English, Croatian, Finnish, and Slovenian: (1) predicting the change of similarity and (2) predicting the human scores of similarity, both of them for a pair of words within two different contexts. We tackled the problem by developing two systems, the first one uses a centroid approach and word vectors. The second one uses the ELMo language model, which is trained for each pair of words with the given context. Our approach achieved the highest score in subtask 2 for the English language.
Anthology ID:
2020.semeval-1.17
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Venue:
SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
150–157
Language:
URL:
https://aclanthology.org/2020.semeval-1.17
DOI:
10.18653/v1/2020.semeval-1.17
Bibkey:
Cite (ACL):
Helena Gomez-Adorno, Gemma Bel-Enguix, Jorge Reyes-Magaña, Benjamín Moreno, Ramón Casillas, and Daniel Vargas. 2020. MineriaUNAM at SemEval-2020 Task 3: Predicting Contextual WordSimilarity Using a Centroid Based Approach and Word Embeddings. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 150–157, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
MineriaUNAM at SemEval-2020 Task 3: Predicting Contextual WordSimilarity Using a Centroid Based Approach and Word Embeddings (Gomez-Adorno et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.17.pdf