网页中商品属性-值关系的自动抽取方法研究.pdfVIP

网页中商品“属性-值”关系的自动抽取方法研究1 2 唐伟 ，洪宇，冯艳卉，姚建民，朱巧明 苏州大学计算机科学与技术学院，苏州，215006 3 E-mail: hongy@ 摘 要：商品属性及其对应值的自动挖掘，对于基于Web 的商品市场需求分析、商品推荐、售后服务等 诸多领域有重要的应用价值。本文提出一种基于模板的方法从结构化网页中抽取完整的商品“属性-值” 关系。该方法包含四个关键技术：1）利用商品网页标题构建领域相关的属性词包；2 ）基于预设分隔符细 化文本节点；3 ）结合领域商品属性词包获取种子“属性-值”关系；4 ）结合网页布局信息和字符信息来 筛选与构建模板。本文的实验基于相机和手机两个领域展开，获得94.68%的准确率和90.57%的召回率。 关键词：商品“属性-值”关系抽取，Web 数据挖掘，模板构建 An Automatic Method for Extracting Product “attribute-value” Pair From the Webpages Tang Wei, Hong Yu, Feng Yan-hui, Yao Jian-min, Zhu Qiao-ming School of Computer Science Technology, Soochow University, Suzhou, 215006 E-mail: hongy@ Abstract: If we represent the products as attributes and attribute values, it will improve the effectiveness of many applications, such as demand forecasting, product recommendations, and product supplier selection. In this paper, we propose a novel method, which is based on the pattern, to extract the “attribute -value” pair of product from structured or semi-structured Web pages. This approach contains four key technologies: 1) acquire domain-specific attributes from titles of Web pages in the same domain. 2) refine text nodes based on some default delimiters. 3) collect seed “attribute-value” pairs based on the domain-specific attributes. 4) construct high-quality patterns by combining specific layout information and character information. The experimental corpus is collected from two domains: digital camera and mobile phone. Experiments show the precision of 94.68% and recall of 90.57% can be got by our method. Keywords: Product “attribute-value” relation extraction, web data mining, template construction 1 引言 互联网技术的高速发展使得在线购物极大普及，国内以淘宝、拍拍为代表的 C2C