ACL RD-TEC 1.0 Summarization of C00-1030
Paper Title:
EXTRACTING THE NAMES OF GENES AND GENE PRODUCTS WITH A HIDDEN MARKOV MODEL
EXTRACTING THE NAMES OF GENES AND GENE PRODUCTS WITH A HIDDEN MARKOV MODEL
Authors: Nigel Collier and Chikashi Nobata and Jun-ichi Tsujii
Primarily assigned technology terms:
- algorithm
- classification
- cross-validation
- databases
- decision trees
- event extraction
- expectation maximization
- finite state
- finite state machines
- hidden markov
- hidden markov model
- hmms
- identification
- iterative learning
- jsing cross-validation
- knowledge discovery
- learning
- learning method
- markov model
- maximum entropy
- maximum entropy model
- maximum-entropy
- maximum-likelihood
- name finding
- part-of-speech tagging
- postprocessing
- predictor
- recognition
- search
- smoothing
- speech recognition
- tagging
- term recognition
- terminology
- tile
- viterbi
- viterbi algorithm
Other assigned terms:
- approach
- backoff
- backoff model
- bigram
- bigram language model
- case
- corpora
- data sets
- data sparseness
- data sparseness problem
- dictionary
- document
- domain model
- entropy
- events
- f-score
- f-score performance
- feature
- feature set
- feature sets
- frequency list
- generalisation
- hmm model
- implementation
- interpolation
- knowledge
- language model
- likelihood
- linear time
- linguistic
- linguistic structures
- long distance dependencies
- medline
- method
- model parameters
- name class
- named entity
- namedentity
- names
- ne task
- nouns
- part-of-speech
- portability
- probabilities
- probability
- probability distributions
- sentence
- sentences
- sparseness problem
- synonymy
- tagged corpora
- term
- terms
- testing set
- text
- training
- training data
- training set
- transition probability
- trees
- understanding
- vocabulary
- word
- word features
- word lists
- word sequence
- words
