What is NER?
Named Entity is a real world object(e.g. Person, Location, Organization), and Named Entity Recognition is a task to identify and locate named entity in text. It’s a key part of information retrival, machine translation, Q&A system etc.
Some Usecases
- Classify Content
Named Entity Recognition can automatically scan entire articles and reveal which are the major people, organizations, and places discussed in them. Knowing the relevant tags for each article help in automatically categorizing the articles in defined hierarchies and enable smooth content discovery. - Efficient Search Algorithms
NER can be run once on all the articles and the relevant entities (tags) associated with each of those articles are stored separately, this could speed up the search process considerably. - Powering Content Recommendations
This can be done by extracting entities from a particular article and recommending the other articles which have the most similar entities mentioned in them.
Techniques
Early Methods
- Dictionary-Based
- Rule-Based
Traditional Machine Learning Methods
- HMM
- MEMM
- CRF
Deep Learning Methods
- LSTM -> LSTM/CNN+CRF -> BiLSTM+CRF -> BiLSTM+CNN+CRF
Recently
- Attention Mechanism
- Transfer Learning
Reference
Named Entity Recognition: Applications and Use Cases
神经网络结构在命名实体识别(NER)中的应用