Modelling the Lexicon in Unsupervised Part of Speech Induction.
Gregory DubbinPhil BlunsomPublished in: CoRR (2014)
Keyphrases
- part of speech
- pos tagging
- syntactic categories
- grammar induction
- unsupervised grammar induction
- pos taggers
- n gram
- training corpus
- natural language processing
- chinese word segmentation
- word sense disambiguation
- dependency parsing
- lexical information
- multiword
- machine translation
- word segmentation
- unsupervised learning
- machine learning
- tf idf
- domain specific
- domain adaptation
- semi supervised learning
- semi supervised
- natural language
- named entity recognition
- text documents
- question answering
- supervised learning
- penn treebank