Extracting Chinese Aliases of Products from the Titles of Selling Webpages
Mei Ni Yang, Hui Sun, Jing Shuang Shen · Applied Mechanics and Materials · 2014
A product always has some different names in Chinese. Getting the aliases of these products is very important in e-commerce, online advertising, etc. Chinese aliases of a product are always placed in the titles of web pages on which this product is sold. Such titles are collected using search engine, and then a conditional random field is used to extract the aliases from them. To improve the performance, distributed representations of words are employed as features in the conditional random field. The method is tested on the real data, and the experimental results are analyzed.