arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.04859cs.CL
收藏

利用视觉特征学习高级组合性

Learning Character-level Compositionality with Visual Features

Carnegie Mellon University(卡内基梅隆大学)

Frederick Liu, Han Lu, Chieh Lo, Graham Neubig

摘要:

以前的工作已经通过创建字符级的意义模型来模拟单词的组合性,减少了罕见单词的稀疏性问题。然而,在许多书写系统中,组合性甚至在字符层面上也有影响:字符的含义是由其部分的总和得出的。在本文中,我们通过创建基于其视觉特征的字符的嵌入,创建字符的图像,并通过卷积神经网络运行它来产生视觉字符嵌入,从而对这种效果进行建模。在文本分类任务上的实验表明,该模型可以更好地处理汉语、日语和韩语等语言中的稀有字符实例。此外,定性分析表明,我们提出的模型学习专注于承载语义内容的字符部分,从而产生在视觉空间中连贯的嵌入。

英文摘要:

Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry semantic content, resulting in embeddings that are coherent in visual space.

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。

↑