ACL RD-TEC 1.0 Summarization of H05-1031
Paper Title:
AUTOMATICALLY LEARNING COGNITIVE STATUS FOR MULTI-DOCUMENT SUMMARIZATION OF NEWSWIRE
AUTOMATICALLY LEARNING COGNITIVE STATUS FOR MULTI-DOCUMENT SUMMARIZATION OF NEWSWIRE
Authors: Ani Nenkova and Advaith Siddharthan and Kathleen McKeown
Primarily assigned technology terms:
- algorithm
- automatic learning
- chunker
- classi cation
- classi er
- computational linguistics
- computing
- content selection
- cross validation
- cross-validation
- data preparation
- document understanding
- feature selection
- human language
- human language technology
- language processing
- language technology
- language tools
- learner
- learning
- machine learning
- matching
- modeling
- multi-document summarization
- natural language processing
- news summarization
- nlp
- noun-phrase chunker
- part-of-speech tagger
- preprocessing
- processing
- pronominalization
- reference realization
- summarization
- summarization systems
- summarizer
- supervised machine learning
- support vector machine
- tagger
- the document understanding
- validation
- weighting
- weka
Other assigned terms:
- annotator
- annotators
- approach
- association for computational linguistics
- bigram
- bigram model
- characters
- classi cation accuracy
- classi cation task
- cluster
- clusters
- co-reference
- cognitive
- cognitive model
- common noun coreference
- coreference information
- discourse
- discourse entity
- distribution
- document
- document set
- document sets
- events
- fact
- feature
- generation
- human annotator
- human communication
- human judgments
- hypothesis
- intelligibility
- keyword
- knowledge
- labeling
- lexical feature
- lexical features
- likelihood
- linguistics
- majority class baseline
- mark-up
- mental model
- name coreference
- named entities
- named entity
- names
- natural language
- natural language tools
- noun phrase
- noun phrases
- opinions
- part-of-speech
- phrase
- precision
- probability
- procedure
- pronoun
- relative clause
- relative clauses
- sentence
- sentences
- signal
- statistics
- support vector
- syntactic form
- technique
- technology
- test data
- test set
- theory
- toolkit
- training
- training data
- understanding
- unigram
- web corpus
- words
- world knowledge
