ACL RD-TEC 1.0 Summarization of P01-1008
Paper Title:
EXTRACTING PARAPHRASES FROM A PARALLEL CORPUS
EXTRACTING PARAPHRASES FROM A PARALLEL CORPUS
Authors: Regina Barzilay and Kathleen R. McKeown
Primarily assigned technology terms:
- algorithm
- alignment process
- alignment technique
- automatic extraction
- binary classifier
- bootstrapping
- chunker
- classification
- classifier
- classifiers
- co-training
- co-training algorithm
- corpus analysis
- corpus-based approach
- cutoff
- database
- disambiguation
- dynamic programming
- entity classification
- extraction technique
- feature extraction
- human language
- identification
- information extraction
- iterative algorithm
- iterative process
- language translation
- learning
- learning algorithm
- lexicon construction
- machine translation
- matching
- multidocument summarization
- named entity classification
- nlp
- paraphrase extraction
- paraphrasing
- parsers
- part-of-speech tagger
- part-of-speech tagging
- preprocessing
- question-answering
- searching
- segmentation
- selective alignment
- sense disambiguation
- sentence alignment
- statistical generation
- statistical parsers
- statistical techniques
- summarization
- tagger
- tagging
- translator
- translators
- unsupervised learning
- unsupervised learning algorithm
- verb phrases
- word sense disambiguation
- word translation
- word-to-word translation
Other assigned terms:
- aligned sentence
- approach
- bilingual corpus
- bilingual lexicons
- case
- chunk
- co-occurrence
- coefficient
- community
- comparable corpora
- compounds
- concept
- concepts
- contextual feature
- contextual features
- corpora
- correlation
- determiner
- english translation
- english translations
- fact
- feature
- feature set
- french
- generation
- generation task
- interpretation
- kappa
- kappa coefficient
- knowledge
- lexical feature
- lexical relations
- lexical resources
- lexicon
- linguistic
- linguists
- local context
- matching process
- meaning
- measures
- mechanisms
- method
- methodology
- modifier
- morphological information
- morphological structure
- n-grams
- named entity
- natural language
- nlp applications
- noise
- non-parallel corpora
- nouns
- pairs of words
- parallel corpora
- parallel corpus
- paraphrase
- paraphrases
- parse
- parse tree
- part-of-speech
- part-of-speech tags
- partof-speech
- phrase
- phrase level
- positive and negative examples
- precision
- predictive power
- preposition
- priori
- procedure
- process
- representations
- running time
- scalability
- seed
- semantic
- sentence
- sentence pair
- sentences
- source language
- source sentence
- source text
- style
- synonyms
- synonymy
- syntactic categories
- syntactic category
- syntactic feature
- syntactic patterns
- system performance
- tags
- target language
- technical terms
- technique
- term
- terms
- test data
- text
- thesaurus
- tokens
- training
- translation pairs
- translations
- tree
- verb
- verb similarity
- word
- word co-occurrence
- word sense
- word similarity
- wordnet
- wordnet thesaurus
- words
