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 1609.04325cs.CL
收藏

在任何有替代语言的语言中的音译

Transliteration in Any Language with Surrogate Languages

University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Stephen Mayhew, Christos Christodoulopoulos, Dan Roth

摘要:

我们介绍了一种音译生成方法,可以在每一种语言中产生音译。如果以前的结果只像维基百科一样多语言,我们将展示如何使用维基百科的训练数据作为任何语言的替代训练。因此,问题变成了按照相对于目标语言的适合性的顺序对维基百科语言进行排名。我们介绍了几个特定于任务的方法来排名语言,并表明我们的方法是甲骨文天花板相媲美,甚至在某些情况下优于它。

英文摘要:

We introduce a method for transliteration generation that can produce transliterations in every language. Where previous results are only as multilingual as Wikipedia, we show how to use training data from Wikipedia as surrogate training for any language. Thus, the problem becomes one of ranking Wikipedia languages in order of suitability with respect to a target language. We introduce several task-specific methods for ranking languages, and show that our approach is comparable to the oracle ceiling, and even outperforms it in some cases.

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。

↑