BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition.
Yinghao LiPranav ShettyLucas LiuChao ZhangLe SongPublished in: ACL/IJCNLP (1) (2021)
Keyphrases
- hidden markov models
- weakly supervised
- named entity recognition
- relation extraction
- named entities
- conditional random fields
- superpixels
- semi supervised
- information extraction
- multiple sources
- natural language processing
- maximum entropy
- co occurrence
- unsupervised learning
- text mining
- question answering
- natural language
- text documents
- data sets
- em algorithm
- input image
- image features
- active learning
- image processing