arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.01489cs.CLcs.LG
收藏

基于复杂网络的词嵌入

Complex networks based word embeddings

Le Mans Université(勒芒大学);Université de Nantes(南特大学)

Nicolas Dugué, Victor Connes

摘要:

大多数情况下,学习词嵌入的第一步是构建词共现矩阵。由于这些矩阵等价于图,因此复杂网络理论自然可以用来处理这些数据。本文考虑将该领域的主要工具社区发现应用于大规模语料库所对应的共现矩阵。社区结构被用来作为一种方式来减少初始空间的维数。使用这种社区结构,我们提出了一种方法来提取词嵌入,是国家的最先进的方法相媲美。

英文摘要:

Most of the time, the first step to learn word embeddings is to build a word co-occurrence matrix. As such matrices are equivalent to graphs, complex networks theory can naturally be used to deal with such data. In this paper, we consider applying community detection, a main tool of this field, to the co-occurrence matrix corresponding to a huge corpus. Community structure is used as a way to reduce the dimensionality of the initial space. Using this community structure, we propose a method to extract word embeddings that are comparable to the state-of-the-art approaches.

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。

↑