ACL RD-TEC 1.0 Summarization of J95-2001
Paper Title:
AUTOMATIC STOCHASTIC TAGGING OF NATURAL LANGUAGE TEXTS
AUTOMATIC STOCHASTIC TAGGING OF NATURAL LANGUAGE TEXTS
Authors: Evangelos Dermataso and George Kokkinakis
Primarily assigned technology terms:
- algorithm
- approximation
- automatic training
- binary search
- capitalization
- categorization
- chi-square test
- classification
- compiler
- computational linguistics
- computing
- fixed-point arithmetic system
- forward-backward algorithm
- grammatical analysis
- hardware
- hidden markov
- hidden markov model
- hidden markov models
- hmm tagger
- hmms
- hyphenation
- language processing
- learning
- lexical acquisition
- likelihood training
- linguistic analysis
- markov model
- maximum likelihood
- maximum likelihood training
- measuring
- morphological analysis
- morphology
- natural language processing
- neural networks
- optimization
- processing
- search
- searching
- stochastic optimization
- stochastic tagger
- stochastic tagging
- tagger
- taggers
- tagging
- tagging process
- training method
- training process
- viterbi
- viterbi algorithm
Other assigned terms:
- ambiguity
- annotated corpora
- approach
- association for computational linguistics
- case
- community
- computational complexity
- conditional probabilities
- conditional probability
- connectionist
- contextual information
- corpora
- determiner
- dictionary
- distribution
- dutch
- english corpus
- english language
- english text
- error rate
- estimation
- events
- experimental results
- french
- french corpus
- french language
- french text
- german corpus
- grammatical categories
- grammatical information
- grammatical structure
- greek language
- hypotheses
- hypothesis
- idiomatic expressions
- implementation
- interpolation
- language model
- lexical entries
- lexicon
- lexicon entries
- lexicon entry
- likelihood
- linguistic
- linguistics
- linguists
- manual intervention
- markov models
- measure
- method
- model parameters
- morphological information
- natural language
- natural language texts
- newspaper corpus
- part-of-speech
- penn treebank
- penn treebank corpus
- preposition
- prepositions
- probabilities
- probability
- probability distribution
- probability distributions
- process
- pronoun
- relation
- sentence
- sentences
- statistics
- stochastic model
- style
- symbols
- syntax
- tag sequence
- tagged text
- tagger lexicon
- tagging model
- tags
- tagset
- technique
- text
- training
- training data
- training text
- transformation
- transition information
- transition probabilities
- treebank
- treebank corpus
- untagged text
- usability
- vocabulary
- word
- word error rate
- word frequency
- word morphology
- words
