The Methods of Machine Learning for Natural Language Information Extraction
自然语言信息抽取中的机器学习方法研究

Information extraction is an effective way of processing various texts, but building a information extraction system is very difficult and time-consuming. In recent years, statistical learning methods for information extraction re- ceive more attention. This paper first deeply analyses the main statistical learning methods employed by researchers in the filed of information extraction and compares the advantages and shortness of various methods. It then explores the solutions to the problem of lack of the training corpus. It also points out the direction for further research in the future.