ACL RD-TEC 1.0 Summarization of C04-1082
Paper Title:
TAGGING WITH HIDDEN MARKOV MODELS USING AMBIGUOUS TAGS
TAGGING WITH HIDDEN MARKOV MODELS USING AMBIGUOUS TAGS
Authors: Alexis Nasr and Frédéric Bechét and Alexandra Volanschi
Primarily assigned technology terms:
- algorithm
- chunker
- chunking
- computing
- database
- hidden markov
- hidden markov model
- hidden markov models
- iterative method
- language modeling
- language processing
- learning
- learning algorithm
- learning procedure
- markov model
- modeling
- natural language processing
- parser
- parsers
- parsing
- part of speech tagging
- pos tagging
- probability estimation
- processing
- search
- search algorithm
- smoothing
- speech tagger
- speech tagging
- statistical language modeling
- supertagging
- syntactic parser
- syntactic parsing
- tag learning
- tagger
- taggers
- tagging
- tagging process
- viterbi
- viterbi algorithm
- viterbi search
- viterbi search algorithm
Other assigned terms:
- adjective
- adverb
- ambiguity
- ambiguity rate
- approach
- baseline model
- brown corpus
- case
- confusion matrix
- convergence
- data sparseness
- device
- distribution
- entropy
- error rate
- estimation
- events
- feature
- gold standard
- hypotheses
- knowledge
- language modeling toolkit
- lexical entry
- lexicon
- linguistic
- markov models
- measure
- measures
- method
- modeling toolkit
- natural language
- nouns
- parse
- part of speech
- penn treebank
- penn treebank tagset
- plural noun
- predictive power
- priori
- probabilistic models
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- processing time
- sentence
- speech tag
- supertag
- supertags
- syntactic constraints
- syntactic probability
- tag sequence
- tagging accuracy
- tags
- tagset
- technique
- test corpus
- toolkit
- training
- training corpus
- training data
- transition probabilities
- treebank
- trigram
- trigram model
- verb
- word
- word classes
- word error rate
- words
