arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.06341cs.CL
收藏

一种面向朝鲜语处理的子字符体系结构

A Sub-Character Architecture for Korean Language Processing

Toyota Technological Institute at Chicago(芝加哥丰田技术研究所)

Karl Stratos

摘要:

我们介绍了一种新颖的子字符架构,利用了独特的组成结构的韩语。我们的方法分解成一个小的一组原始的语音单位称为jamo字母的字符和单词级表示诱导每个字符。jamo字母泄露了传统字符级单元难以访问的语法和语义信息。它们极大地缓解了数据稀疏性问题,将观测空间减少到原始空间的1.6%,同时提高了我们实验的准确性。我们将我们的架构应用于依存句法分析,并在强大的词汇基线上取得了显着的改善。

英文摘要:

We introduce a novel sub-character architecture that exploits a unique compositional structure of the Korean language. Our method decomposes each character into a small set of primitive phonetic units called jamo letters from which character- and word-level representations are induced. The jamo letters divulge syntactic and semantic information that is difficult to access with conventional character-level units. They greatly alleviate the data sparsity problem, reducing the observation space to 1.6% of the original while increasing accuracy in our experiments. We apply our architecture to dependency parsing and achieve dramatic improvement over strong lexical baselines.

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。

↑