ACL RD-TEC 1.0 Summarization of N04-1042
Paper Title:
ACCURATE INFORMATION EXTRACTION FROM RESEARCH PAPERS USING CONDITIONAL RANDOM FIELDS
ACCURATE INFORMATION EXTRACTION FROM RESEARCH PAPERS USING CONDITIONAL RANDOM FIELDS
Authors: Fuchun Peng and Andrew McCallum
Primarily assigned technology terms:
- algorithm
- citation analysis
- classifier
- classifiers
- computing
- conditional random field
- conditional random fields
- crfs
- cross-validation
- dynamic programming
- entity extraction
- entropy learning
- error rate reduction
- error reduction
- feature engineering
- feature induction
- feature selection
- finite state
- finite state machine
- good-turing smoothing
- hidden markov
- hidden markov models
- hmms
- induction
- information extraction
- information retrieval
- language modeling
- language processing
- learning
- learning algorithms
- learning procedure
- learning techniques
- likelihood estimation
- machine learning
- machine learning techniques
- matching
- maximum entropy
- maximum entropy classifiers
- maximum likelihood
- maximum likelihood estimation
- measuring
- meta-data extraction
- modeling
- name entity extraction
- natural language processing
- normalization
- optimization
- parsing
- processing
- rate reduction
- regularization
- search
- search engines
- sequence labeling
- shallow parsing
- smoothing
- smoothing method
- soft feature selection
- spelling
- table extraction
- viterbi
- viterbi algorithm
- viterbi inference
Other assigned terms:
- approach
- benchmark
- benchmark data set
- break
- case
- citation
- conditional probability
- data set
- data sets
- distribution
- entropy
- entropy models
- error rate
- estimation
- evaluation metrics
- experimental results
- exponential distribution
- extraction problem
- f-measure
- feature
- feature space
- feature types
- first-order model
- gaussian prior
- generative model
- graph structure
- hmm model
- independence assumption
- information gain
- intention
- keyword
- labeling
- lexicon
- likelihood
- likelihood function
- log-likelihood
- log-linear models
- markov models
- maximum entropy models
- measure
- measures
- meta-data
- method
- model structure
- name entity
- names
- natural language
- noise
- performance comparison
- precision
- prior distribution
- probabilities
- probability
- procedure
- process
- regular expressions
- sentence
- standard benchmark
- svms
- technique
- term
- theory
- training
- training data
- training set
- transition probabilities
- word
- word error rate
- words
