ACL RD-TEC 1.0 Summarization of P06-2019

Paper Title:
CONSTRAINT-BASED SENTENCE COMPRESSION: AN INTEGER PROGRAMMING APPROACH

Authors: James Clarke and Mirella Lapata

Other assigned terms:

  • american news corpus
  • annotators
  • approach
  • appropriate compression model
  • association for computational linguistics
  • broadcast news
  • broadcast news corpus
  • case
  • compression corpus
  • concepts
  • content words
  • corpora
  • corpus evidence
  • decision-tree model
  • determiners
  • document
  • entropy
  • estimation
  • evaluations
  • fact
  • feature
  • feature set
  • generation
  • gold standard
  • grammar
  • grammatical relations
  • grammaticality
  • head noun
  • heuristics
  • knowledge
  • labeling
  • language model
  • language model probability
  • language modeling toolkit
  • large corpus
  • large-scale lexicon
  • lexical information
  • lexicon
  • likelihood
  • linguistic
  • linguistic constraints
  • linguistic knowledge
  • linguistics
  • local context
  • meaning
  • method
  • model parameters
  • model probability
  • modeling toolkit
  • modifier
  • negation
  • news corpus
  • optimisation problem
  • parallel corpora
  • parallel corpus
  • parse
  • parse tree
  • parsing paradigm
  • personal pronouns
  • phrase
  • portability
  • preposition
  • prepositional phrases
  • probabilities
  • probability
  • process
  • programming approach
  • pronouns
  • relation
  • role labeling
  • search space
  • semantic
  • semantic role
  • sentence
  • sentence compression problem
  • sentence structure
  • sentences
  • server
  • significance score
  • statistics
  • support vector
  • symbol
  • syntactic constituent
  • syntactic information
  • syntactic knowledge
  • syntactic structure
  • syntactic tree
  • technology
  • television
  • term
  • terms
  • test corpora
  • test set
  • text
  • text corpus
  • tokens
  • toolkit
  • training
  • training data
  • training set
  • tree
  • trees
  • trigram
  • trigram model
  • unigram
  • unigram language model
  • verb
  • vocabulary
  • vocabulary size
  • word
  • word order
  • word pair
  • word sequences
  • wordnet
  • words
  • ziff-davis corpus

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***