ACL RD-TEC 1.0 Summarization of J05-3002

Paper Title:
SENTENCE FUSION FOR MULTIDOCUMENT NEWS SUMMARIZATION

Primarily assigned technology terms:

Other assigned terms:

  • adjective
  • aligned corpus
  • alignment problem
  • anaphoric expression
  • anaphoric expressions
  • anchors
  • approach
  • association for computational linguistics
  • bag of words
  • bias
  • bilingual dictionary
  • biology
  • bleu
  • canonical form
  • case
  • cluster
  • clusters
  • coherence
  • cohesion
  • concept
  • context-free grammar
  • cosine similarity
  • dependency representation
  • dependency structure
  • dependency structures
  • dependency tree
  • dependency trees
  • dependency-based representation
  • determiners
  • dictionary
  • discourse
  • discourse level
  • distribution
  • document
  • domain-specific knowledge
  • english translations
  • entropy
  • error rate
  • evaluation function
  • evaluation methodology
  • events
  • f-measure
  • fact
  • feature
  • forest
  • generation
  • generation process
  • generation strategy
  • grammar
  • grammar rules
  • grammatical category
  • grammatical features
  • grammaticality
  • human judgments
  • human performance
  • hypothesis
  • implementation
  • input text
  • intelligence
  • interpretation
  • kappa
  • knowledge
  • language model
  • language modeling toolkit
  • language models
  • large comparable news corpus
  • large training
  • lattice
  • lexical chain
  • lexical chains
  • lexical choice
  • lexical information
  • lexical items
  • lexicon
  • likelihood
  • linguistic
  • linguistic knowledge
  • linguistic representation
  • linguistics
  • local context
  • mapping
  • mappings
  • maps
  • meaning
  • measure
  • measures
  • method
  • methodology
  • modeling toolkit
  • modifier
  • mood
  • multigen architecture
  • multigen summarization system
  • named entity
  • natural language
  • negation
  • news corpus
  • noise
  • noun phrase
  • noun phrases
  • nouns
  • paraphrase
  • paraphrases
  • parse
  • parse tree
  • particle
  • particles
  • phrase
  • phrase structure
  • polarity
  • precision
  • predicate-argument
  • predicate-argument structure
  • prepositional phrases
  • prepositions
  • priori
  • probability
  • procedure
  • process
  • punctuation
  • regression model
  • relative clause
  • relative clauses
  • reordering
  • representations
  • root node
  • search procedure
  • search space
  • segments
  • semantic
  • semantic information
  • semantic interpretation
  • semantic representation
  • semantic role
  • sentence
  • sentence representation
  • sentence structure
  • sentences
  • similarity function
  • similarity measure
  • similarity measures
  • similarity score
  • similarity scores
  • similarity threshold
  • source text
  • sources of information
  • statistics
  • subcategorization frames
  • substring
  • subtree
  • subtrees
  • synonyms
  • synset
  • synsets
  • syntactic context
  • syntactic function
  • syntactic parse
  • syntactic trees
  • syntax
  • system development
  • system performance
  • technique
  • technology
  • terms
  • test corpus
  • test data
  • test set
  • text
  • text collection
  • text corpus
  • textual information
  • textual input
  • theoretical computer science
  • toolkit
  • topics
  • topology
  • training
  • training corpus
  • transformation
  • translations
  • tree
  • trees
  • trigram
  • trigram model
  • understanding
  • verb
  • verb phrase
  • web page
  • weighting scheme
  • well-formed sentence
  • word
  • word distribution
  • word order
  • word similarity
  • wordnet
  • wordnet synsets
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***