BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition.
Yinghao LiPranav ShettyLucas LiuChao ZhangLe SongPublished in: CoRR (2021)
Keyphrases
- hidden markov models
- weakly supervised
- named entity recognition
- relation extraction
- named entities
- conditional random fields
- superpixels
- semi supervised
- information extraction
- natural language processing
- multiple sources
- maximum entropy
- co occurrence
- text mining
- question answering
- text documents
- domain specific
- active learning
- expert systems
- computer vision
- machine learning
- databases
- em algorithm
- unsupervised learning
- knowledge discovery
- pairwise
- reinforcement learning