ACL RD-TEC 1.0 Summarization of W01-1011
Paper Title:
GIST-IT: COMBINING LINGUISTIC AND MACHINE LEARNING TECHNIQUES FOR EMAIL SUMMARIZATION
GIST-IT: COMBINING LINGUISTIC AND MACHINE LEARNING TECHNIQUES FOR EMAIL SUMMARIZATION
Authors: Evelyne Tzoukermann and Smaranda Muresan and Judith L. Klavans
Primarily assigned technology terms:
- algorithm
- automatic extraction
- automatic text processing
- categorization
- chunker
- classification
- classifier
- classifiers
- clustering
- computing
- data collection
- decision tree
- decision trees
- disambiguation
- document gisting
- document indexing
- email message summarizer
- feature selection
- finite-state transducer
- forest classifier
- genetic algorithms
- gisting
- head clustering
- identification
- indexing
- induction
- induction learning
- information extraction
- information management
- information retrieval
- information retrieval task
- key phrase extraction
- knowledge management
- learning
- learning algorithms
- learning approach
- learning system
- learning techniques
- linguistic processing
- linguistic techniques
- listing
- machine learning
- machine learning algorithms
- machine learning approach
- machine learning techniques
- morphological processing
- nlp
- normalization
- noun phrase extraction
- np chunker
- np extraction
- parsing
- phrase extraction
- pos tagger
- pos tagging
- processing
- query refinement
- regression
- rule induction
- rule learning
- semantic parsing
- sense disambiguation
- shallow text processing
- splitting
- summarization
- summarization method
- summarization system
- summarizer
- supervised machine learning
- symbolic learning
- symbolic machine learning
- tagger
- tagging
- text categorization
- text classifier
- text processing
- text-to-speech
- tokenization
- transducer
- user interface
- verb phrases
- word sense disambiguation
Other assigned terms:
- affix
- approach
- bias
- brown corpus
- case
- characters
- classification model
- classification task
- corpora
- data set
- determiners
- document
- document content
- email message
- experimental results
- extraction problem
- fact
- feature
- feature vector
- feature vectors
- forest
- genre
- gold standard
- heuristics
- hypothesis
- inflection
- information gain
- key phrase
- knowledge
- lexicon
- linguistic
- linguistic approach
- linguistic intuition
- linguistic knowledge
- meaning
- measure
- measures
- message
- metadata
- method
- modifier
- n-gram
- n-grams
- nlp applications
- nlp tasks
- noise
- normalization factor
- noun phrase
- noun phrase length
- noun phrases
- nouns
- opinion
- paragraph
- paragraphs
- phrase
- phrase meaning
- phrase structure
- precision
- preposition
- prepositional phrases
- preprocessor
- probabilistic models
- process
- query
- relation
- retrieval task
- semantic
- semantic content
- sentence
- sentence level
- sentences
- sparse data
- summarization task
- syntactic constituents
- syntactic head
- synthesized speech
- system architecture
- system performance
- tagger lexicon
- technique
- technology
- terms
- testing set
- text
- text type
- tf \* idf
- topics
- training
- training data
- training phase
- training set
- tree
- trees
- user
- verb
- web documents
- web pages
- word
- word sense
- words
