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 1810.03595cs.CL
收藏

基于图像嵌入的端到端文本分类

End-to-End Text Classification via Image-based Embedding using Character-level Networks

Hosei University(法政大学)

Shunsuke Kitada, Ryunosuke Kotani, Hitoshi Iyatomi

摘要:

为了基于形态分析来分析和/或理解诸如日语、汉语和泰语的没有词边界的语言,期望在词嵌入之前执行适当的分词。但在这些语言中,这本身就很困难。近年来,基于深度学习的各种语言模型取得了显著进展,其中一些利用字符级特征的方法成功地避免了这样的难题。然而,当模型被输入上述语言的字符级特征时,由于大量的字符类型,它经常会导致过拟合。在本文中,我们提出了一个CE-CLCNN,字符级卷积神经网络使用字符编码器来解决这些问题。所提出的CE-CLCNN是一个端到端的学习模型,并且具有基于图像的字符编码器,即CE-CLCNN将目标文档中的每个字符作为图像处理。通过各种实验,我们发现并证实了我们的CE-CLCNN捕获了视觉和语义相似字符的紧密嵌入特征,并在几个开放文档分类任务中取得了最先进的结果。在本文中,我们报告了CE-CLCNN在维基百科标题估计任务中的性能,并分析了内部行为。

英文摘要:

For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate word segmentation before word embeddings. But it is inherently difficult in these languages. In recent years, various language models based on deep learning have made remarkable progress, and some of these methodologies utilizing character-level features have successfully avoided such a difficult problem. However, when a model is fed character-level features of the above languages, it often causes overfitting due to a large number of character types. In this paper, we propose a CE-CLCNN, character-level convolutional neural networks using a character encoder to tackle these problems. The proposed CE-CLCNN is an end-to-end learning model and has an image-based character encoder, i.e. the CE-CLCNN handles each character in the target document as an image. Through various experiments, we found and confirmed that our CE-CLCNN captured closely embedded features for visually and semantically similar characters and achieves state-of-the-art results on several open document classification tasks. In this paper we report the performance of our CE-CLCNN with the Wikipedia title estimation task and analyse the internal behaviour.

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。

↑