ACL RD-TEC 1.0 Summarization of P06-1089
Paper Title:
GUESSING PARTS-OF-SPEECH OF UNKNOWN WORDS USING GLOBAL INFORMATION
GUESSING PARTS-OF-SPEECH OF UNKNOWN WORDS USING GLOBAL INFORMATION
Authors: Tetsuji Nakagawa and Yuji Matsumoto
Primarily assigned technology terms:
- algorithm
- approximation
- binary feature function
- computational linguistics
- conditional random fields
- crfs
- cross validation
- cross validation method
- cross-validation
- decoding
- disambiguation
- dynamic programming
- entity recognition
- generalized iterative scaling
- gibbs sampling
- hmms
- information extraction
- iterative scaling
- language analysis
- language processing
- learning
- maximum entropy
- maximum entropy model
- model parameter estimation
- model-based method
- modeling
- named entity recognition
- natural language processing
- nlp
- orientation extraction
- parameter estimation
- parsers
- pos tagging
- processing
- processor
- reading
- recognition
- sampling
- semi-supervised learning
- sense disambiguation
- simulated annealing
- splitting
- splitting method
- tagging
- tagging system
- two-fold cross validation
- unsupervised learning
- validation
- viterbi
- viterbi decoding
- word sense disambiguation
Other assigned terms:
- alphabet
- ambiguity
- annotators
- approach
- association for computational linguistics
- binary feature
- case
- characters
- chinese treebank
- collocation
- conditional distribution
- corpora
- correlation
- dictionaries
- discourse
- distribution
- document
- edr corpus
- entity recognition task
- entropy
- entropy models
- estimation
- experimental results
- feature
- genia
- genia corpus
- gold standard
- hapax legomena
- human annotators
- interpolation
- joint distribution
- joint probability
- kanji
- katakana
- kyoto university corpus
- language models
- linguistics
- local context
- log-linear models
- markov chain
- maximum entropy models
- meaning
- method
- model parameter
- model parameters
- named entities
- named entity
- natural language
- nlp task
- nlp tasks
- nouns
- part-of-speech
- parts-of-speech
- penn chinese treebank
- penn treebank
- pfr corpus
- pos tag
- posterior
- probabilistic model
- probabilistic models
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- recognition task
- semantic
- semantic orientation extraction
- sentence
- sentences
- statistical models
- suffixes
- susanne corpus
- symbol
- syntactic features
- syntactic functions
- tagged corpora
- tags
- technique
- term
- test data
- text
- training
- training data
- training examples
- training phase
- treebank
- treebank corpus
- treebank wsj corpus
- trigram
- verb
- verb meaning
- window size
- word
- word sense
- words
- wsj corpora
- wsj corpus
