ACL RD-TEC 1.0 Summarization of M98-1009
Paper Title:
BBN: DESCRIPTION OF THE SIFT SYSTEM AS USED FOR MUC-7
BBN: DESCRIPTION OF THE SIFT SYSTEM AS USED FOR MUC-7
Authors: S. Miller and M. Crystal and H. Fox and L. Ramshaw and R. Schwartz and R. Stone and R. Weischedel and the Annotation Group
Primarily assigned technology terms:
- algorithm
- bracketing
- capitalization
- classifier
- database
- decoder
- dynamic programming
- entity extraction
- entity extraction system
- entity recognition
- extraction system
- hmm-based approach
- information extraction
- inquery system
- learning
- learning algorithm
- matching
- maximum likelihood
- measuring
- named entity extraction
- named entity recognition
- orthographic representation
- parser
- parsing
- post-processing
- processing
- pruning
- reading
- recognition
- sampling
- scoring
- search
- search process
- searching
- semantic annotation
- smoothing
- smoothing method
- spelling
- statistical parser
- string matching
- training algorithm
- training procedure
- training process
- viterbi
- viterbi algorithm
- witten-bell smoothing
Other assigned terms:
- annotated corpus
- annotated training corpus
- annotation
- annotation strategy
- annotators
- approach
- bigram
- bigram language model
- bigram model
- break
- broadcast news
- case
- case information
- characters
- classifier model
- co-reference
- derivation
- determiners
- distribution
- document
- english sentence
- entity type
- extraction process
- f score
- f-measure
- fact
- feature
- feature value
- gazetteer
- generation
- generation process
- generative probability
- head word
- heuristic
- hmm model
- hmm-based model
- implementation
- interpretation
- joint probability
- knowledge
- language model
- language models
- likelihood
- matching process
- measure
- message
- method
- modifier
- muc-3
- muc-7 ne
- named entities
- named entity
- named entity task
- names
- ne task
- noun phrase
- organization names
- paragraph
- parse
- parse tree
- part-of-speech
- part-of-speech tag
- part-of-speech tags
- parts of speech
- penn treebank
- penn treebank corpus
- person names
- phrase
- precision
- prepositions
- prior probability
- probabilities
- probability
- procedure
- process
- pronouns
- proper name
- punctuation
- recognition errors
- relation
- sbar
- sbar structure
- semantic
- semantic label
- semantic relations
- semantic relationships
- semantic structure
- semantic structures
- semantic tag
- sentence
- sentence level
- sentence structure
- sentence-level model
- sentences
- set size
- signal
- speech input
- statistical model
- statistics
- structural feature
- structure of the sentence
- subtree
- syntactic information
- syntactic interpretation
- syntactic parse
- syntactic structure
- syntax
- syntax and semantics
- system performance
- tags
- te task
- technology
- television
- term
- test data
- test set
- text
- text corpus
- trained model
- training
- training corpus
- training data
- training set
- training set size
- transcribed speech
- tree
- tree structure
- treebank
- treebank corpus
- trees
- vocabulary
- vocabulary size
- wall street journal text
- word
- word features
- words
