论文标题
用于文本分类任务的SVM与预训练的语言模型（PLM）的比较
A Comparison of SVM against Pre-trained Language Models (PLMs) for Text Classification Tasks
论文作者
论文摘要
预先训练的语言模型（PLM）的出现在许多自然语言处理（NLP）任务（包括文本分类）方面取得了巨大的成功。由于使用这些模型时没有最小的功能工程，因此PLM成为任何NLP任务的事实上的选择。但是，对于特定领域的语料库（例如财务，法律和工业），对特定任务进行了预先培训的模型进行了微调，这表明可以提高性能。在本文中，我们比较了三个无公共域数据集上的四个不同PLM的性能和一个包含特定域单词的现实世界数据集与带有TFIDF矢量化文本的简单SVM线性分类器。四个数据集上的实验结果表明，使用PLM，即使进行微调，也不能比线性SVM分类器提供显着增益。因此，我们建议对于文本分类任务，传统的SVM以及仔细的功能工程可以比PLMS更便宜，更高的性能。
The emergence of pre-trained language models (PLMs) has shown great success in many Natural Language Processing (NLP) tasks including text classification. Due to the minimal to no feature engineering required when using these models, PLMs are becoming the de facto choice for any NLP task. However, for domain-specific corpora (e.g., financial, legal, and industrial), fine-tuning a pre-trained model for a specific task has shown to provide a performance improvement. In this paper, we compare the performance of four different PLMs on three public domain-free datasets and a real-world dataset containing domain-specific words, against a simple SVM linear classifier with TFIDF vectorized text. The experimental results on the four datasets show that using PLMs, even fine-tuned, do not provide significant gain over the linear SVM classifier. Hence, we recommend that for text classification tasks, traditional SVM along with careful feature engineering can pro-vide a cheaper and superior performance than PLMs.
