Evaluating the Generalization Property of Prefix-based Methods for Data-to-text Generation

Clarine Vongpaseut, Alberto Lumbreras, Mike Gartrell, Patrick Gallinari


Abstract
Fine-tuning is the prevalent paradigm to adapt pre-trained language models to downstream tasks. Lightweight fine-tuning methods, such as prefix-tuning, only tune a small set of parameters which alleviates cost. Such methods were shown to achieve results similar to fine-tuning; however, performance can decrease when the inputs get farther from the training domain. Moreover, latest works questioned the efficiency of recent lightweight fine-tuning techniques depending on the task and the size of the model. In this paper, we propose to evaluate the generalization property of prefix-based methods depending on the size of the pre-trained language model in the multi-domain setting on data-to-text generation. We found that their performance depends heavily on the size of the model.
Anthology ID:
2023.jeptalnrecital-short.8
Volume:
Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 2 : travaux de recherche originaux -- articles courts
Month:
6
Year:
2023
Address:
Paris, France
Editors:
Christophe Servan, Anne Vilnat
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
73–81
Language:
URL:
https://aclanthology.org/2023.jeptalnrecital-short.8
DOI:
Bibkey:
Cite (ACL):
Clarine Vongpaseut, Alberto Lumbreras, Mike Gartrell, and Patrick Gallinari. 2023. Evaluating the Generalization Property of Prefix-based Methods for Data-to-text Generation. In Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 2 : travaux de recherche originaux -- articles courts, pages 73–81, Paris, France. ATALA.
Cite (Informal):
Evaluating the Generalization Property of Prefix-based Methods for Data-to-text Generation (Vongpaseut et al., JEP/TALN/RECITAL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.jeptalnrecital-short.8.pdf