Unsupervised Part-of-Speech Disambiguation for High Frequency Words and Its Influence on Unsupervised Parsing.
Christian HänigPublished in: CICLing (2010)
Keyphrases
- pos tagging
- syntactic categories
- high frequency
- part of speech
- word sense disambiguation
- low frequency
- natural language processing
- chinese word segmentation
- n gram
- pos taggers
- word segmentation
- machine translation
- dependency parsing
- wordnet
- unsupervised learning
- high resolution
- wavelet transform
- unknown words
- subband
- domain adaptation
- training corpus
- multiword
- penn treebank
- word sense
- semi supervised
- information retrieval
- semantic role labeling
- noun phrases
- linguistic information
- search engine
- machine learning
- dependency parser
- web documents
- feature set