ACL RD-TEC 1.0 Summarization of J02-4002

Paper Title:
ARTICLES SUMMARIZING SCIENTIFIC ARTICLES: EXPERIMENTS WITH RELEVANCE AND RHETORICAL STATUS

Authors: Simone Teufel and Marc Moens

Primarily assigned technology terms:

Other assigned terms:

  • 10-fold cross-validation
  • academic writing
  • analogy
  • anaphora
  • annotation
  • annotation scheme
  • annotator
  • annotators
  • approach
  • argumentation
  • association for computational linguistics
  • background information
  • bayesian model
  • beam
  • break
  • case
  • citation
  • citation feature
  • classification accuracy
  • classification performance
  • cluster
  • clustering procedure
  • clusters
  • coefficient
  • composition
  • computational linguistics domain
  • concept
  • concepts
  • confusion matrix
  • content selection step
  • content words
  • contextual information
  • contingency table
  • corpora
  • correlation
  • cue phrases
  • data set
  • data sets
  • data sparseness
  • dialogue act
  • discourse
  • discourse context
  • discourse structure
  • distribution
  • document
  • document frequency
  • document structure
  • domain knowledge
  • entropy
  • events
  • f-measure
  • fact
  • feature
  • finite clause
  • finite verb
  • frequency counts
  • generation
  • genre
  • gold standard
  • grammar
  • grammatical relations
  • heuristic
  • heuristics
  • human annotation
  • human annotator
  • human annotators
  • human judgment
  • human judgments
  • human performance
  • idiomatic expressions
  • implementation
  • intrinsic system
  • inverse document frequency
  • kappa
  • kappa coefficient
  • kappa value
  • knowledge
  • lexical choice
  • lexicon
  • linguistic
  • linguistic features
  • linguistics
  • location information
  • log-likelihood
  • log-likelihood measure
  • main verb
  • meaning
  • measure
  • measures
  • method
  • methodology
  • modality
  • n-grams
  • named entity
  • names
  • natural language
  • negation
  • noise
  • noun phrases
  • nouns
  • paragraph
  • paragraphs
  • part-of-speech
  • past participle
  • posterior
  • posterior probability
  • precision
  • predicates
  • prepositional phrases
  • prior probability
  • probabilities
  • probability
  • probability distributions
  • procedure
  • process
  • pronoun
  • random sample
  • real-world text
  • redundant information
  • regular expression pattern
  • regular expressions
  • relation
  • rhetorical information
  • rhetorical status
  • rhetorical structure
  • scientific writing
  • segments
  • semantic
  • semantic class
  • semantic classes
  • semantic similarity
  • sentence
  • sentence pair
  • sentences
  • signal
  • similarity measure
  • source text
  • statistics
  • stem
  • stochastic model
  • style
  • surface similarity measure
  • syntax
  • system evaluation
  • system performance
  • tagged corpora
  • tags
  • technology
  • term
  • term frequency
  • terms
  • text
  • textual structure
  • tf \* idf
  • theory
  • topics
  • trained model
  • training
  • training data
  • training material
  • training phase
  • training time
  • tree
  • trees
  • understanding
  • uniform distribution
  • user
  • verb
  • verb class
  • verb classes
  • verb lexicon
  • verb similarity
  • word
  • word association
  • word classes
  • word frequency
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***