Publication Type
Journal Article
Version
acceptedVersion
Publication Date
4-2022
Abstract
Transfer learning plays an essential role in Deep Learning, which can remarkably improve the performance of the target domain, whose training data is not sufficient. Our work explores beyond the common practice of transfer learning with a single pre-trained model. We focus on the task of Vietnamese sentiment classification and propose LIFA, a framework to learn a unified embedding from several pre-trained models. We further propose two more LIFA variants that encourage the pre-trained models to either cooperate or compete with one another. Studying these variants sheds light on the success of LIFA by showing that sharing knowledge among the models is more beneficial for transfer learning. Moreover, we construct the AISIA-VN-Review-F dataset, the first large-scale Vietnamese sentiment classification database. We conduct extensive experiments on the AISIA-VN-Review-F and existing benchmarks to demonstrate the efficacy of LIFA compared to other techniques. To contribute to the Vietnamese NLP research, we publish our source code and datasets to the research community upon acceptance.
Keywords
LIFA, Low-resource NLP, Mixture of experts, Sentiment classification, Transfer learning
Discipline
Databases and Information Systems | East Asian Languages and Societies
Publication
Information Sciences
Volume
590
First Page
1
Last Page
14
ISSN
0020-0255
Identifier
10.1016/j.ins.2021.12.059
Publisher
Elsevier
Citation
Nguyen, Cuong V.; Le, Khiem H.; PHAM, Hong Quang; Pham, Quang H.; and Nguyen, Binh T..
Learning for amalgamation: A multi-source transfer learning framework for sentiment classification. (2022). Information Sciences. 590, 1-14.
Available at: https://ink.library.smu.edu.sg/sis_research/6948
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1016/j.ins.2021.12.059