ACL RD-TEC 1.0 Summarization of W06-3309
Paper Title:
GENERATIVE CONTENT MODELS FOR STRUCTURAL ANALYSIS OF MEDICAL ABSTRACTS
GENERATIVE CONTENT MODELS FOR STRUCTURAL ANALYSIS OF MEDICAL ABSTRACTS
Authors: Jimmy Lin and Damianos Karakos and Dina Demner-Fushman and Sanjeev Khudanpur
Primarily assigned technology terms:
- algorithm
- approximation
- baum-welch estimation
- binary classification
- classification
- classifiers
- clustering
- computational linguistics
- computing
- cross-validation
- data preparation
- decision-making
- discourse modeling
- discriminant analysis
- document summarization
- forward-backward algorithm
- hidden markov
- hidden markov model
- hidden markov models
- hmm-based approach
- hmms
- htk toolkit
- indexing
- information systems
- language modeling
- language processing
- learning
- learning techniques
- linear discriminant
- linear discriminant analysis
- machine learning
- machine learning techniques
- markov model
- maximum likelihood
- modeling
- monitoring
- multi-way classification
- natural language processing
- processing
- question answering
- question answering system
- recognition
- sentence classification
- speech recognition
- sri language modeling
- structural analysis
- summarization
- summarization system
- support vector machines
- ten-fold cross-validation
- unsupervised approach
- viterbi
Other assigned terms:
- annotation
- annotation process
- approach
- backoff
- benchmark
- bias
- bigram
- case
- classification accuracy
- classification error
- classification error rate
- classification performance
- classification task
- classification tasks
- corpora
- decision-making process
- device
- discourse
- discourse structure
- document
- error rate
- estimation
- evaluations
- experimental results
- f-measure
- fact
- generative models
- genre
- hypothesis
- language modeling toolkit
- language models
- language processing applications
- lexical features
- likelihood
- linear complexity
- linguistics
- mapping
- markov models
- measure
- measures
- medline
- metadata
- modeling toolkit
- natural language
- natural language processing applications
- ontologies
- precision
- probabilities
- probability
- procedure
- process
- projection
- query
- questionnaire
- semantic
- semantic features
- sentence
- sentences
- standard benchmark
- statistics
- support vector
- svms
- symbol
- technique
- term
- terms
- test collection
- text
- text genre
- toolkit
- trained model
- training
- training data
- training examples
- training set
- transition probability
- word
- word sequences
- words
