arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.03099cs.IR
收藏

多参考余弦:一种大集合中文本相似性度量的新方法

Multi-reference Cosine: A New Approach to Text Similarity Measurement in Large Collections

Hamid Mohammadi, Amin Nikoukaran

摘要:

一个高效、可扩展的文档相似性检测系统的重要性是不可否认的。搜索引擎需要批量文本相似性度量来检测其索引中的重复和接近重复的网页,以防止多次索引网页。此外,在评分阶段,搜索引擎需要相似性度量来检测网页上的重复内容,以提高其结果的质量。结合降维技术和信息增益理论的思想,提出了一种批量文本相似性检测的新方法。新方法的重点是搜索引擎需要检测重复和接近重复的网页。在NEWS20数据集上对新方法进行了测试,结果表明,新方法在速度和性能上都优于余弦文本相似度算法。最重要的是,它比其他竞争对手的方法,Simhash相似度算法更快,更准确.

英文摘要:

The importance of an efficient and scalable document similarity detection system is undeniable nowadays. Search engines need batch text similarity measures to detect duplicated and near-duplicated web pages in their indexes in order to prevent indexing a web page multiple times. Furthermore, in the scoring phase, search engines need similarity measures to detect duplicated contents on web pages so as to increase the quality of their results. In this paper, a new approach to batch text similarity detection is proposed by combining some ideas from dimensionality reduction techniques and information gain theory. The new approach is focused on search engines need to detect duplicated and near-duplicated web pages. The new approach is evaluated on the NEWS20 dataset and the results show that the new approach is faster than the cosine text similarity algorithm in terms of speed and performance. On top of that, It is faster and more accurate than the other rival method, Simhash similarity algorithm.

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。

↑