arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.13012cs.CLcs.LGstat.ML
收藏

比较 BERT 与传统机器学习文本分类

Comparing BERT against traditional machine learning text classification

Santiago González-Carvajal, Eduardo C. Garrido-Merchán

AI总结:

本文通过多场景实验比较 BERT 与基于 TF-IDF 的传统机器学习文本分类,证明 BERT 性能更优且不受文本语言等特征影响,支持其作为 NLP 默认方法。

摘要:

近年来,BERT 模型已成为一种流行的先进机器学习模型,能够处理监督式文本分类等多种 NLP 任务,而无需人工监督。它能够灵活处理任何类型的语料库并取得优异结果,这使得该方法不仅在学术界,而且在工业界都非常受欢迎。尽管如此,多年来仍有许多不同方法被成功使用。在本研究中,我们首先介绍 BERT,并对经典 NLP 方法作简要综述。随后,我们通过一组涵盖不同场景的实验,实证检验 BERT 相对于将传统 TF-IDF 词汇表输入机器学习算法这一做法的行为表现。本研究的目的是补充实证证据,以支持或拒绝将 BERT 作为 NLP 任务的默认选择。实验表明,BERT 具有优越性,并且其表现独立于 NLP 问题的各项特征,例如文本语言,这为将 BERT 用作 NLP 问题的默认技术提供了实证依据。

英文摘要:

The BERT model has arisen as a popular state-of-the-art machine learning model in the recent years that is able to cope with multiple NLP tasks such as supervised text classification without human supervision. Its flexibility to cope with any type of corpus delivering great results has make this approach very popular not only in academia but also in the industry. Although, there are lots of different approaches that have been used throughout the years with success. In this work, we first present BERT and include a little review on classical NLP approaches. Then, we empirically test with a suite of experiments dealing different scenarios the behaviour of BERT against the traditional TF-IDF vocabulary fed to machine learning algorithms. Our purpose of this work is to add empirical evidence to support or refuse the use of BERT as a default on NLP tasks. Experiments show the superiority of BERT and its independence of features of the NLP problem such as the language of the text adding empirical evidence to use BERT as a default technique to be used in NLP problems.

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。

↑