WarwickNLP at SemEval-2024 Task 1: Low-Rank Cross-Encoders for Efficient Semantic Textual Relatedness

Fahad Ebrahim, Mike Joy


Abstract
This work participates in SemEval 2024 Task 1 on Semantic Textural Relatedness (STR) in Track A (supervised regression) in two languages, English and Moroccan Arabic. The task consists of providing a score of how two sentences relate to each other. The system developed in this work leveraged a cross-encoder with a merged fine-tuned Low-Rank Adapter (LoRA). The system was ranked eighth in English with a Spearman coefficient of 0.842, while Moroccan Arabic was ranked seventh with a score of 0.816. Moreover, various experiments were conducted to see the impact of different models and adapters on the performance and accuracy of the system.
Anthology ID:
2024.semeval-1.38
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:
246–252
Language:
URL:
https://aclanthology.org/2024.semeval-1.38
DOI:
10.18653/v1/2024.semeval-1.38
Bibkey:
Cite (ACL):
Fahad Ebrahim and Mike Joy. 2024. WarwickNLP at SemEval-2024 Task 1: Low-Rank Cross-Encoders for Efficient Semantic Textual Relatedness. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 246–252, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
WarwickNLP at SemEval-2024 Task 1: Low-Rank Cross-Encoders for Efficient Semantic Textual Relatedness (Ebrahim & Joy, SemEval 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.semeval-1.38.pdf
Supplementary material:
 2024.semeval-1.38.SupplementaryMaterial.zip
Supplementary material:
 2024.semeval-1.38.SupplementaryMaterial.txt