ACL RD-TEC 1.0 Summarization of N04-2002
Paper Title:
IDENTIFYING CHEMICAL NAMES IN BIOMEDICAL TEXT: AN INVESTIGATION OF SUBSTRING CO-OCCURRENCE BASED APPROACHES
IDENTIFYING CHEMICAL NAMES IN BIOMEDICAL TEXT: AN INVESTIGATION OF SUBSTRING CO-OCCURRENCE BASED APPROACHES
Primarily assigned technology terms:
- algorithm
- bayes system
- bayesian approach
- classification
- classification algorithm
- classification approach
- classifiers
- computing
- cross validation
- database
- decision trees
- decoding
- dynamic programming
- dynamic programming algorithm
- entity recognition
- extraction system
- good-turing smoothing
- grouping
- identification
- information extraction
- information extraction system
- language identification
- learning
- learning task
- matching
- modeling
- modeling technique
- naive bayes
- naive bayes classifiers
- naive bayes system
- named entity recognition
- parameter tuning
- programming algorithm
- recognition
- significance testing
- smoothing
- smoothing techniques
- splitting
- support vector machines
- tokenization
- tuning
- validation
- viterbi
- viterbi decoding
Other assigned terms:
- annotation
- approach
- bayesian framework
- binomial distribution
- biomedical domain
- biomedical text
- boundary information
- case
- classification rule
- co-occurrence
- co-occurrence information
- co-occurrence statistics
- conditional independence
- development set
- dictionary
- distribution
- estimation
- geometric mean
- grid
- human involvement
- hypothesis
- identification task
- independence assumption
- interpolation
- interpolation coefficients
- kullback-leibler divergence
- manual annotation
- measure
- medline
- method
- model parameters
- n-gram
- n-gram model
- n-gram models
- n-grams
- named entity
- named entity task
- names
- noise
- normal distribution
- null hypothesis
- precision
- prior probability
- probabilities
- probability
- probability model
- punctuation
- random sample
- recognition task
- smoothing parameter
- statistical model
- statistics
- substring
- support vector
- symbols
- tags
- technique
- term
- test data
- testing data
- text
- text corpus
- theory
- tokens
- training
- training and testing data
- training data
- training text
- trees
- word
- word senses
- words
