GIL-IIMAS UNAM at SemEval-2024 Task 1: SAND: An In Depth Analysis of Semantic Relatedness Using Regression and Similarity Characteristics

Francisco Lopez-ponce, Ángel Cadena, Karla Salas-jimenez, Gemma Bel-enguix, David Preciado-márquez


Abstract
The STR shared task aims at detecting the degree of semantic relatedness between sentence pairs in multiple languages. Semantic relatedness relies on elements such as topic similarity, point of view agreement, entailment, and even human intuition, making it a broader field than sentence similarity. The GIL-IIMAS UNAM team proposes a model based in the SAND characteristics composition (Sentence Transformers, AnglE Embeddings, N-grams, Sentence Length Difference coefficient) and classical regression algorithms. This model achieves a 0.83 Spearman Correlation score in the English test, and a 0.73 in the Spanish counterpart, finishing just above the SemEval baseline in English, and second place in Spanish.
Anthology ID:
2024.semeval-1.186
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1288–1292
Language:
URL:
https://aclanthology.org/2024.semeval-1.186
DOI:
Bibkey:
Cite (ACL):
Francisco Lopez-ponce, Ángel Cadena, Karla Salas-jimenez, Gemma Bel-enguix, and David Preciado-márquez. 2024. GIL-IIMAS UNAM at SemEval-2024 Task 1: SAND: An In Depth Analysis of Semantic Relatedness Using Regression and Similarity Characteristics. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1288–1292, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
GIL-IIMAS UNAM at SemEval-2024 Task 1: SAND: An In Depth Analysis of Semantic Relatedness Using Regression and Similarity Characteristics (Lopez-ponce et al., SemEval 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.semeval-1.186.pdf
Supplementary material:
 2024.semeval-1.186.SupplementaryMaterial.txt
Supplementary material:
 2024.semeval-1.186.SupplementaryMaterial.zip