ACL RD-TEC 1.0 Summarization of W93-0305
Paper Title:
HMM-BASED PART-OF-SPEECH TAGGING FOR CHINESE CORPORA
HMM-BASED PART-OF-SPEECH TAGGING FOR CHINESE CORPORA
Authors: Chao-Huang Chang and Cheng-der Chen
Primarily assigned technology terms:
- algorithm
- automatic tagging
- automatic word segmentation
- baum-welch reestimation
- bootstrap
- chinese part-of-speech tagging
- chinese word segmentation
- classification
- clause identification
- corpus preparation
- decoder
- decoding
- dictionary look-up
- error analysis
- hidden markov
- hidden markov model
- hmm tagger
- identification
- identification system
- information processing
- information retrieval
- language processing
- learning
- machine translation
- machine translation systems
- markov model
- modeling
- natural language processing
- nlp
- nominalization
- part-of-speech tagging
- postprocessing
- preprocessing
- processing
- recognition
- reestimation
- segmentation
- segmentation algorithm
- speech recognition
- speech tagger
- tagger
- tagging
- tagging process
- tagging system
- text-to-speech
- tile
- training process
- translation systems
- unsupervised learning
- viterbi
- viterbi decoder
- viterbi decoding
- word identification
- word segmentation
Other assigned terms:
- adjective
- adverb
- ambiguous words
- brown corpus
- case
- characters
- chinese characters
- chinese corpora
- chinese corpus
- chinese part-of-speech
- chinese word
- clusters
- compound words
- compounds
- concept
- confusion matrix
- corpora
- cpu time
- dictionary
- distribution
- error rate
- experimental results
- first-order model
- foreign words
- idiomatic expressions
- knowledge
- language model
- lexical entries
- lexicon
- linguistic
- linguists
- lob corpus
- local constraints
- manual tagging
- measure
- model parameters
- mood
- natural language
- nouns
- observation probability distribution
- part-of-speech
- part-of-speech tag
- part-of-speech tags
- particles
- parts-of-speech
- preposition
- prepositions
- probabilities
- probability
- probability distribution
- procedure
- process
- pronouns
- segmented corpus
- semantic
- sentences
- syntactic information
- tag sequence
- tag set
- tagged corpora
- tagged corpus
- tagged text
- tagging accuracy
- tagging model
- tags
- technology
- testing corpora
- testing data
- text
- text type
- tokens
- trained model
- training
- training data
- transition matrix
- transition probability
- untagged corpus
- untagged text
- verb
- word
- word frequencies
- word sequence
- words
