Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)

Alessio Miaschi, Felice Dell’Orletta, Giulia Venturi


Abstract
In this paper, we explore the impact of augmenting pre-trained Encoder-Decoder models, specifically T5, with linguistic knowledge for the prediction of a target task. In particular, we investigate whether fine-tuning a T5 model on an intermediate task that predicts structural linguistic properties of sentences modifies its performance in the target task of predicting sentence-level complexity. Our study encompasses diverse experiments conducted on Italian and English datasets, employing both monolingual and multilingual T5 models at various sizes. Results obtained for both languages and in cross-lingual configurations show that linguistically motivated intermediate fine-tuning has generally a positive impact on target task performance, especially when applied to smaller models and in scenarios with limited data availability.
Anthology ID:
2024.lrec-main.922
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
10539–10554
Language:
URL:
https://aclanthology.org/2024.lrec-main.922
DOI:
Bibkey:
Cite (ACL):
Alessio Miaschi, Felice Dell’Orletta, and Giulia Venturi. 2024. Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10539–10554, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It) (Miaschi et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.922.pdf