Information Extraction

Date: 23.05.09

Writer: 9tailwolf : doryeon514@gm.gist.ac.kr

Introduction

Most of texts are unstructured data. Information Extraction is a method that find useful data in unstructured text data. In NLP, to find useful data in text, we need some regular structured dat that include meaning relationship between Entity.

Learning Information Extraction

Learning Information Extraction process is as follows.

1. Sentence Classification
2. Tokenization
3. Part of speech tagging
4. Named Entity Recognition
5. Relation Extraction

Rule Based Relation Extraction

Defined the rule to find relation. If you have more information, redefined rule.

DL Based Relation Extraction

• Hidden Markov Model
• Matimum Entropy Model
• Conditional Random Field
• Naive Bayes Network
• Desision Tree