arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09115cs.CV
收藏

融合学习:一个情感分类的多源迁移学习框架

Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification

AISIA Research Lab(AISIA研究实验室);University of Science(科学大学);Vietnam National University, Ho Chi Minh City(胡志明市越南国家大学);Singapore Management University(新加坡管理大学)

Cuong V. Nguyen, Khiem H. Le, Anh M. Tran, Quang H. Pham, Binh T. Nguyen

摘要:

迁移学习在深度学习中起着重要作用,它可以显著提高目标域在训练数据不足时的性能。我们的工作超越了使用单个预训练模型的迁移学习的常见做法。我们专注于越南语情感分类的任务,并提出了LIFA,这是一个从几个预训练模型中学习统一嵌入的框架。我们还提出了另外两种LIFA变体,鼓励预先训练的模型相互合作或竞争。研究这些变量揭示了LIFA的成功,表明在模型之间共享知识对迁移学习更有益。此外,我们还构建了第一个大规模越南情感分类数据库AISIA-VN-Review-F数据集。我们对AISIA-VN-Review-F和现有基准进行了广泛的实验,以证明LIFA与其他技术相比的有效性。为了促进越南NLP研究,我们在接受后向研究社区发布我们的源代码和数据集。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑