基于双语语料库的短语复述实例获取研究  

Phrasal Paraphrase Acquisition Based on Bilingual Corpus

作　　者：李维刚[1] 刘挺[1] 李生[1] 

机构地区：[1]哈尔滨工业大学计算机学院信息检索研究室,黑龙江哈尔滨150001

出　　处：《中文信息学报》2007年第5期112-117,共6页Journal of Chinese Information Processing

基　　金：国家自然科学基金(60503072;60575042;60435020)

摘　　要：本文提出一种基于双语语料库的短语复述实例获取方法,尤其能够很好的抽取歧义短语的复述实例。该方法通过输入一个双语短语对约束短语的语义,利用词对齐的双语语料库,构造一个双向抽取模型从中抽取双语对的复述实例。双向抽取模型通过比较每一个候选复述短语和输入短语之间的语义一致性,来确定每个候选是否成为最终的复述实例。实验结果表明,本文短语复述实例获取方法的综合准确率达到了60%,获取了较好的性能。In this paper a novel method based on bilingual corpus is proposed to extract phrasal paraphrase examples. We focus on extract paraphrases of ambiguous phrases. A bilingual pair is the original input. Then all candidate paraphrases are extracted from word aligned bilingual corpus. The bi-direction model is designed to acquire confident paraphrases according to the coherence between the candidate phrases and the input phrases. The experimental results show that thesynthesis precision is about 60%.

关 键 词：计算机应用 中文信息处理 复述实例 复述获取 短语复述 双语语料库 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]