Coarse-to-Fine Pre-training for Named Entity Recognition.
Mengge XueBowen YuZhenyu ZhangTingwen LiuYue ZhangBin WangPublished in: EMNLP (1) (2020)
Keyphrases
- coarse to fine
- named entity recognition
- information extraction
- named entities
- multiscale
- multiresolution
- natural language processing
- semi supervised
- text summarization
- maximum entropy
- image registration
- conditional random fields
- object detection
- hierarchical segmentation
- relation extraction
- dynamic programming
- training set
- classifier ensemble
- image pyramid
- annotated corpus
- co occurrence
- expert systems
- pattern recognition
- feature selection
- maximum entropy classifier
- machine learning
- structured prediction
- question answering
- text mining
- supervised learning
- hidden markov models
- pairwise
- knowledge base
- artificial intelligence