ACL RD-TEC 1.0 Summarization of W05-0405
Paper Title:
FEATURE-BASED SEGMENTATION OF NARRATIVE DOCUMENTS
FEATURE-BASED SEGMENTATION OF NARRATIVE DOCUMENTS
Authors: David Kauchak and Francine Chen
Primarily assigned technology terms:
- 3-fold cross validation
- algorithm
- analyzer
- classi cation
- classi er
- co-reference resolution
- cross validation
- cross-validation
- ellipsis resolution
- entity extraction
- entity extraction system
- entity extractor
- extraction system
- extractor
- feature extraction
- feature selection
- grouping
- information access
- knowledge representation
- learning
- learning algorithm
- learning method
- likelihood ratio test
- maximum entropy
- morphological analyzer
- named entity extraction
- navigation
- nlp
- preprocessing
- question answering
- ratio test
- re-training
- segmentation
- selection process
- speech tagger
- stringent chaining
- summarization
- support vector machines
- tagger
- text analysis
- text segmentation
- text summarization
- texttiling
- tokenizer
- topic segmentation
- two-fold cross-validation
- validation
- weighting
- weka
Other assigned terms:
- anaphora
- anaphoric expressions
- approach
- baseline performance
- binary feature
- broadcast news
- broadcast news data
- case
- chain length
- co-reference
- cohesion
- content words
- conversation
- correlation
- correlations
- cosine similarity
- cosine similarity measure
- cue phrases
- data set
- data sets
- distribution
- document
- ellipsis
- empirical results
- encyclopedia
- entropy
- error rate
- evaluation measures
- evaluation metrics
- exponential model
- expository text
- feature
- feature types
- feature-based approach
- heuristic
- human performance
- information content
- information source
- information sources
- japanese text
- knowledge
- labeling
- length distribution
- lexical chain
- lexical chains
- lexical cohesion
- likelihood
- likelihood ratio
- likelihood-ratio
- linguistic
- linguistic features
- linguistic knowledge
- measure
- measures
- method
- mutual information
- n-grams
- named entities
- named entity
- names
- narrative text
- natural language
- nlp tasks
- paragraph
- paragraphs
- part of speech
- parts of speech
- precision
- priori
- probabilities
- probability
- procedure
- process
- pronoun
- research and development
- segment boundaries
- segment boundary
- segmentation problem
- segments
- semantic
- semantic network
- semantic networks
- sentence
- sentences
- similarity measure
- similarity metric
- similarity score
- similarity scores
- similarity table
- sources of information
- sparse data
- standard deviation
- style
- support vector
- svms
- synonyms
- synonymy
- tags
- technology
- term
- terms
- test data
- test set
- testing data
- text
- text documents
- text structure
- topics
- training
- training data
- training set
- vocabulary
- word
- word frequency
- wordnet
- wordnet hierarchy
- words
