arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.06279cs.CLcs.SI
收藏

利用词嵌入提高共现文本网络的可区分性

Using word embeddings to improve the discriminability of co-occurrence text networks

Institute of Mathematics;Computer Science, Department of Computer Science, University of S\ a o Paulo, S\ a o Carlos, SP, Brazil

Laura V. C. Quispe, Jorge A. V. Tohalino, Diego R. Amancio

摘要:

词汇共现网络已被用于分析文本的实际和理论场景。尽管在一些应用中取得了相对成功,但传统的共现网络无法在文本中出现距离较远的相似单词之间建立联系。在这里,我们调查是否使用词嵌入作为一种工具,以创建虚拟链接的同现网络可以提高分类系统的质量。我们的研究结果表明,在风格测量任务的可辨别性提高时,使用手套,Word2Vec和FastText。此外,我们发现,当停止字不被忽视,并使用一个简单的全局阈值策略来建立虚拟链接时,得到了优化的结果。由于所提出的方法能够改善文本作为复杂网络的表示,我们相信它可以扩展到研究其他自然语言处理任务。同样,理论语言研究可以受益于所采用的丰富的表示词共现网络。

英文摘要:

Word co-occurrence networks have been employed to analyze texts both in the practical and theoretical scenarios. Despite the relative success in several applications, traditional co-occurrence networks fail in establishing links between similar words whenever they appear distant in the text. Here we investigate whether the use of word embeddings as a tool to create virtual links in co-occurrence networks may improve the quality of classification systems. Our results revealed that the discriminability in the stylometry task is improved when using Glove, Word2Vec and FastText. In addition, we found that optimized results are obtained when stopwords are not disregarded and a simple global thresholding strategy is used to establish virtual links. Because the proposed approach is able to improve the representation of texts as complex networks, we believe that it could be extended to study other natural language processing tasks. Likewise, theoretical languages studies could benefit from the adopted enriched representation of word co-occurrence networks.

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。

↑