arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02857cs.CL
收藏

真正低资源语言的低资源依存句法分析方法的系统比较

A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages

University of Edinburgh(爱丁堡大学);University of Copenhagen(哥本哈根大学)

Clara Vania, Yova Kementchedjhieva, Anders Søgaard, Adam Lopez

摘要:

解析器只适用于世界上少数几种语言,因为它们需要大量的训练数据。仅仅使用少量的训练数据,我们能走多远?我们系统地比较了一组简单的策略,以改善低资源解析器:数据增强,这还没有被测试过;跨语言的培训;和音译。通过对三种类型多样的低资源语言--北萨米语、加利西亚语和哈萨克语--的实验,我们发现:(1)当只有低资源树库可用时,数据增强非常有用;(2)当相关的高资源树库可用时,跨语言训练是有用的,并且补充了数据增强;(3)当高资源树库使用不同的书写系统时,音译到共享的正字法空间中也是非常有帮助的。

英文摘要:

Parsers are available for only a handful of the world's languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strategies for improving low-resource parsers: data augmentation, which has not been tested before; cross-lingual training; and transliteration. Experimenting on three typologically diverse low-resource languages---North Sámi, Galician, and Kazah---We find that (1) when only the low-resource treebank is available, data augmentation is very helpful; (2) when a related high-resource treebank is available, cross-lingual training is helpful and complements data augmentation; and (3) when the high-resource treebank uses a different writing system, transliteration into a shared orthographic spaces is also very helpful.

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。

↑