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 1908.02579cs.CL
收藏

一种简单有效的文本分类预训练词嵌入微调方法

A Simple and Effective Approach for Fine Tuning Pre-trained Word Embeddings for Improved Text Classification

Center of Informatics Sciences, Nile University(尼罗河大学信息科学中心)

Amr Al-Khatib, Samhaa R. El-Beltagy

摘要:

这项工作提出了一种新的和简单的方法微调预训练的词嵌入的文本分类任务。在这种方法中,术语出现的类在微调过程中充当额外的上下文变量,并为该术语的最终词向量做出贡献。因此,在特定类别中有区别地使用的单词将承载在嵌入空间中彼此更接近的向量,并且将对该类别更具歧视性。为了验证这种新的方法,它被应用到三个阿拉伯语和两个英语数据集,以前已用于文本分类任务,如情感分析和情感检测。在绝大多数情况下,使用所提出的方法获得的结果,大大改善。

英文摘要:

This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning process, and contributes to the final word vector for that term. As a result, words that are used distinctively within a particular class, will bear vectors that are closer to each other in the embedding space and will be more discriminative towards that class. To validate this novel approach, it was applied to three Arabic and two English datasets that have been previously used for text classification tasks such as sentiment analysis and emotion detection. In the vast majority of cases, the results obtained using the proposed approach, improved considerably.

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。

↑