中文关系抽取技术研究

A Comprehensive Review on Relation Extraction

在网络数据杂乱繁多的今天,信息抽取越来越受到重视,而关系抽取作为信息抽取的一个重要研究方向也倍受学者们的关注.在对关系抽取的发展历史进行回顾的基础上,阐述了近五年里关系抽取研究中的主要方法和思路.根据关系抽取中所采用的不同技术,对比分析了他们在模型思路及技术实现上的异同,同时对优势和劣势比较了分析.最后,对关系抽取任务中存在的难点问题进行了阐述,并提出了未来可能的解决思路,旨在为关系抽取技术的进一步发展和应用提供有效的说明和借鉴.

Entity Relation Extraction is an important part of Information Extraction,and it is paid more and more attention in the chaotic network data.On the basis of reviewing the development history of relation extraction,the main methods and ideas of the technical literature in relation extraction research are analyzed and expounded in recent five years.According to the different technology adopted by relation extraction task,this paper discusses the model and implementation method of relation extraction,and compares the strengths and weaknesses of each method.Then it points out the problem of mainstream methods and analysis of possible solutions of future,in order to provide an effective illustration and reference for the further development and application of relational extraction.