News Abridgement Algorithm Based on Word Alignment and Syntactic Parsing

摘要

The rapid development of new media results in a lot of redundant information, increasing the difficulty of quickly obtaining useful information and browsing simplified messages on portable devices. Thus emerges the automatic news abridgement technology. We propose a novel method of word alignment, aiming at news headlines, applying the combination method of statistics and rules to intelligent abridgement. And a new framework based on the combination of sentence abridgement and sentence selection to generate the abridgement result of news contents, abridging the original text to the word limit, in order to achieve the uttermost conservation of the original meaning. Meanwhile, for a fair and intelligent evaluation, this paper presents an evaluation method of automatic summarization specific to sentence abridgement techniques. Experimental results show that the proposed methods are feasible, and able to automatically generate coherent and representative summaries of given news with high density.