ACL RD-TEC 1.0 Summarization of P01-1039
Paper Title:
INFORMATION EXTRACTION FROM VOICEMAIL
INFORMATION EXTRACTION FROM VOICEMAIL
Authors: Jing Huang and Geoffrey Zweig and Mukund Padmanabhan
Primarily assigned technology terms:
- algorithm
- automatic stochastictransducer induction
- automaton
- beam search
- classification
- cross-validation
- cutoff
- cutoff method
- database
- document retrieval
- entity detection
- entity extraction
- entity tagging
- entropy estimation
- estimation procedure
- feature selection
- finite state
- finite state automata
- finite state transducers
- incremental feature selection
- induction
- induction algorithm
- induction process
- information extraction
- information pertaining
- learning
- maxent
- maximum entropy
- maximum entropy approach
- maximum entropy framework
- maximum entropy model
- maximum-entropy
- modeling
- named entity detection
- named entity extraction
- named entity tagging
- normalization
- part-of-speech tagging
- predictor
- recognition
- recognition system
- recognizer
- rule-based approach
- rule-based system
- search
- speech recognition
- speech recognition system
- speech recognizer
- spoken document retrieval
- stochastictransducer
- stochastictransducer induction
- structure induction
- tagger
- tagging
- training procedure
- transcription
- transducer
- transducer induction
- transducers
- transduction
- voicemail
Other assigned terms:
- acyclic graph
- approach
- automata
- background model
- beam
- bigram
- break
- broadcast news
- case
- classification tasks
- conditional probability
- conversational speech
- data sparsity
- dictionary
- distribution
- document
- entropy
- error rate
- estimation
- evaluation test
- experimental results
- f-measure
- fact
- feature
- grammar
- hierarchical structure
- hypotheses
- implementation
- information content
- labeled training data
- language model
- leaf
- lexical features
- likelihood
- mapping
- maxent model
- message
- method
- named entities
- named entity
- named entity task
- names
- ne task
- nist
- part-of-speech
- pauses
- perplexity
- phrase
- phrase attachment
- precision
- prepositional phrase
- prepositional phrase attachment
- probabilities
- probability
- procedure
- process
- proper names
- query
- segments
- speech data
- statistical models
- suffix
- suffixes
- symbol
- symbols
- tagging problem
- tags
- technique
- technology
- terms
- test data
- test set
- text
- training
- training data
- training examples
- transcribed speech
- transcriptions
- transcripts
- transition probabilities
- tree
- uniform distribution
- unigram
- unigram language model
- vocabulary
- word
- word error rate
- word sequence
- word sequences
- words
