arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.05014cs.CL
收藏

基于双语词嵌入图的语言分类

Language classification from bilingual word embedding graphs

TU Darmstadt(达姆施塔特工业大学);Goethe University(歌德大学)

Steffen Eger, Armin Hoenen, Alexander Mehler

摘要:

我们在单语语义评价任务中研究了第二语言在双语词嵌入中的作用。我们发现,下游任务的表现和第二语言的相似性目标语言之间的强和弱的正相关。此外,我们展示了如何双语词嵌入可以用于语义语言分类的任务,联合语义空间在第二语言中有意义的方式不同。我们的研究结果支持这一假设,语义语言相似性的影响,结构相似性以及地理/接触。

英文摘要:

We study the role of the second language in bilingual word embeddings in monolingual semantic evaluation tasks. We find strongly and weakly positive correlations between down-stream task performance and second language similarity to the target language. Additionally, we show how bilingual word embeddings can be employed for the task of semantic language classification and that joint semantic spaces vary in meaningful ways across second languages. Our results support the hypothesis that semantic language similarity is influenced by both structural similarity as well as geography/contact.

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。

↑