ACL RD-TEC 1.0 Summarization of W06-1655
Paper Title:
A HYBRID MARKOV/SEMI-MARKOV CONDITIONAL RANDOM FIELD FOR SEQUENCE SEGMENTATION
A HYBRID MARKOV/SEMI-MARKOV CONDITIONAL RANDOM FIELD FOR SEQUENCE SEGMENTATION
Primarily assigned technology terms:
- algorithm
- bayes classifier
- chinese word segmentation
- chunking
- classification
- classifier
- computational linguistics
- computing
- conditional likelihood
- conditional random field
- conditional random fields
- crfs
- decoding
- decomposition
- discriminative classifier
- error reduction
- feature mapping
- forward-backward algorithm
- language processing
- logistic regression
- machine translation
- machine translation system
- modeling
- named-entity recognition
- natural language processing
- nlp
- parameter estimation
- parameter estimation and inference
- parsing
- processing
- recognition
- regression
- regularization
- scoring
- segmentation
- sequence segmentation
- shallow parsing
- statistical nlp
- text classification
- thresholding
- translation system
- viterbi
- viterbi algorithm
- word segmentation
- word segmentation bakeoff
- word segmentation task
Other assigned terms:
- affixes
- approach
- association for computational linguistics
- baseline model
- bias
- bigram
- cache
- case
- character sequence
- characters
- chinese word
- chinese words
- chunk
- chunks
- classification task
- conditional probabilities
- conditional probability
- crf model
- cubic time
- development set
- discriminative model
- distribution
- estimation
- events
- f-measure
- fact
- feature
- feature set
- feature sets
- feature type
- feature value
- feature vector
- feature vectors
- generative model
- generative models
- knowledge
- labeling
- language model
- likelihood
- linguistics
- log-linear model
- log-linear models
- logistic regression model
- mapping
- meaning
- method
- model parameters
- named-entity
- natural language
- parse
- probabilities
- probability
- punctuation
- punctuation marks
- regression model
- relation
- relative frequency
- representations
- segmentation bakeoff
- segmentation problem
- segments
- sentence
- sentences
- sequence model
- set size
- statistics
- suffix
- technique
- terms
- test set
- text
- text classification task
- tokens
- training
- training corpus
- training data
- training example
- training examples
- training set
- training set size
- translations
- trees
- unigram
- weight vector
- word
- word boundaries
- words
