Research On Kernel Based Entity Relation Extraction

There are huge amount of documents on the Internet. How to extract the most useful information from the Internet is still a challenge. IE (Information Extraction) techniques address this problem. The main target of IE is transforming the free text into structural or semi-structural information for diversified applications such as question answering and so on.There are three major tasks in IE which are Named Entity Tagging, Entity Relation Extraction and Event Detection. Entity Relation Extraction is not only one of the important tasks in IE but also the foundation for Event Detection and many other applications. The major task of RE (Relation Extraction) is to search and determine the particular relations between one kind of named entity and another kind of named entity. Current RE approaches can be categorized in to 4 major types: Repository-based algorithms, Feature-based machine learning algorithms, Kernel-based machine learning algorithms and Pattern-based bootstrapping algorithms.