Bigram HMM with Context Distribution Clustering for Unsupervised Chinese Part-of-Speech tagging.
Lidan ZhangKwok-Ping ChanChunyu KitDongfeng CaiPublished in: CIPS-SIGHAN (2010)
Keyphrases
- chinese word segmentation
- unsupervised learning
- pos tagging
- word segmentation
- hidden markov models
- clustering algorithm
- unsupervised clustering
- clustering method
- unsupervised feature selection
- spectral clustering
- machine learning
- unsupervised manner
- part of speech
- cluster validation
- supervised learning
- semi supervised
- cluster analysis
- n gram
- information bottleneck
- agglomerative clustering
- unsupervised classification
- completely unsupervised
- information retrieval
- natural language understanding
- dependency parsing
- named entity recognition
- data clustering
- conditional random fields
- speech recognition
- contextual information
- context aware
- k means
- normalized cut
- chinese characters
- dependency parser
- handwritten word recognition