首页 | 本学科首页   官方微博 | 高级检索  
     

复述技术研究综述
引用本文:刘挺,李维刚,张宇,李生.复述技术研究综述[J].中文信息学报,2006,20(4):27-34.
作者姓名:刘挺  李维刚  张宇  李生
作者单位:哈尔滨工业大学计算机学院信息检索研究室
摘    要:复述是自然语言中比较普遍的一个现象,它集中反映了语言的多样性。复述研究的对象主要是短语或者句子的同义现象。自然语言处理各种底层技术的不断发展和成熟,为复述研究提高了可能,使之受到越来越多的关注。在英文和日文方面,复述技术已经被成功的应用到信息检索、自动问答、信息抽取、自动文摘以及机器翻译等多个领域,有效地提高了系统的性能。本文主要对复述实例库的构建、复述规则的抽取以及复述的生成等几方面的最新研究进展进行详细的综述,并简要介绍了我们在中文复述方面进行的初步研究工作。在文章的最后一部分,我们对复述技术的难点及未来的发展方向进行了展望,并对全文进行了总结。

关 键 词:人工智能  自然语言处理  综述  句子复述  复述语料库  复述抽取  复述生成  
文章编号:1003-0077(2006)04-0025-08
收稿时间:2005-08-09
修稿时间:2006-06-05

A Survey on Paraphrasing Technology
LIU Ting,LI Wei-gang,ZHANG Yu,LI Sheng.A Survey on Paraphrasing Technology[J].Journal of Chinese Information Processing,2006,20(4):27-34.
Authors:LIU Ting  LI Wei-gang  ZHANG Yu  LI Sheng
Affiliation:Information Retrieval Laboratory , School of Computer Science & Technology , Haerbin Institute of Technology
Abstract:Paraphrase is a common phenomenon in natural language which captures core aspects of variability in language.The study of paraphrase is about the synonymy phenomena of phrases or sentences.With the development of foundation technology of natural language processing,research on paraphrase has been recently received growing attention.Currently,paraphrasing technology has been applied in many NLP fields,such as,information retrieval,question answering,information extraction,automatic text summarization,machine translation and text watermark,to improve the performance of these systems.This paper will mainly survey several aspects of paraphrasing technology as followed: paraphrases corpus construction,paraphrases rules extraction,paraphrases generation and paraphrase evaluation.And some of our work about paraphrase are also introduced in brief.At the last section,some challenges,together with the future directions of paraphrasing technology are indicated.
Keywords:artifical intelligence  natural language processing  overview  sentence paraphrasing  paraphrases corpus  paraphrases extraction  paraphrases generation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中文信息学报》浏览原始摘要信息
点击此处可从《中文信息学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号