arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.02423cs.CL
收藏

形态学词嵌入

Morphological Word Embeddings

Johns Hopkins University(约翰斯·霍普金斯大学);University of Munich(慕尼黑大学)

Ryan Cotterell, Hinrich Schütze

摘要:

语言的相似性是多方面的。例如,两个单词可以在语义、句法或词法等方面相似。连续词嵌入已经被证明在某种程度上捕捉了这些相似性的大部分。这项工作考虑用形态注释数据指导词嵌入,这是一种半监督学习的形式,鼓励向量对词的形态进行编码,即,在嵌入空间中接近的词共享形态特征。为此,我们扩展了对数双线性模型,并表明我们的学习嵌入确实实现了这一点,使用德国作为案例研究。

英文摘要:

Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some degree. This work considers guiding word-embeddings with morphologically annotated data, a form of semi-supervised learning, encouraging the vectors to encode a word's morphology, i.e., words close in the embedded space share morphological features. We extend the log-bilinear model to this end and show that indeed our learned embeddings achieve this, using German as a case study.

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。

↑