arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.07601cs.CL
收藏

基于词根和词缀的词嵌入评价方法

Evaluation method of word embedding by roots and affixes

School of Computer Science and Engineering(计算机科学与工程学院);Beihang University(北京航空航天大学)

KeBin Peng

摘要:

词嵌入在许多自然语言处理任务中已被证明是非常有效的。然而,现有的模型在解释词向量的维度方面仍然存在一些局限性。本文提出了一种从自然语言的内在结构出发来解释词根词缀的新方法--词根词缀模型(RAAM)。它也可以作为评价词嵌入质量的一个指标。我们在模型中引入了信息熵的概念,并将维度分为词根和词缀两类。然后把每个类别作为一个整体来考虑,而不是单独考虑。我们尝试了英文维基百科语料库。我们的研究结果表明,这两个属性之间存在负线性关系,我们的模型和下游的语义评估任务之间有很高的正相关性。

英文摘要:

Word embedding has been shown to be remarkably effective in a lot of Natural Language Processing tasks. However, existing models still have a couple of limitations in interpreting the dimensions of word vector. In this paper, we provide a new approach---roots and affixes model(RAAM)---to interpret it from the intrinsic structures of natural language. Also it can be used as an evaluation measure of the quality of word embedding. We introduce the information entropy into our model and divide the dimensions into two categories, just like roots and affixes in lexical semantics. Then considering each category as a whole rather than individually. We experimented with English Wikipedia corpus. Our result show that there is a negative linear relation between the two attributes and a high positive correlation between our model and downstream semantic evaluation tasks.

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。

↑