ACL RD-TEC 1.0 Summarization of W03-1004
Paper Title:
SENTENCE ALIGNMENT FOR MONOLINGUAL COMPARABLE CORPORA
SENTENCE ALIGNMENT FOR MONOLINGUAL COMPARABLE CORPORA
Authors: Regina Barzilay and Noemie Elhadad
Primarily assigned technology terms:
- algorithm
- alignment algorithm
- alignment method
- automatic induction
- classification
- clustering
- corpus alignment
- data collection
- decomposition
- document summarization
- dynamic programming
- hidden markov
- hidden markov model
- induction
- learning
- link clustering
- local alignment
- machine translation
- markov model
- matching
- monolingual sentence alignment
- multidocument summarization
- nlp
- off-line processing
- paragraph mapping
- parameter tuning
- paraphrasing
- processing
- search
- search process
- searching
- sentence alignment
- single document summarization
- structure induction
- summarization
- text compression
- text generation
- text simplification
- text-to-text generation
- topic detection
- tuning
- unsupervised method
Other assigned terms:
- aligned sentence
- annotation
- annotator
- annotators
- approach
- background information
- case
- classification task
- cluster
- cluster number
- clusters
- communication knowledge
- comparable corpora
- comparable corpus
- content words
- contextual information
- corpora
- cosine measure
- detection task
- document
- document text
- domain communication knowledge
- encyclopedia
- encyclopedia britannica
- events
- feature
- function words
- generation
- genre
- human annotation
- human annotator
- hypotheses
- implementation
- knowledge
- lexical resources
- lexical similarity
- mapping
- mapping rules
- measure
- method
- monolingual corpora
- monolingual corpus
- names
- noise
- noun phrase
- paragraph
- paragraphs
- parallel corpora
- paraphrase
- paraphrases
- phrase
- process
- proper name
- proper names
- proper noun
- russian
- semantic
- semantic structure
- sentence
- sentence level
- sentence pair
- sentence similarity
- sentences
- similarity function
- similarity measure
- statistics
- style
- tags
- testing set
- text
- text structure
- topic structure
- topics
- training
- training set
- training time
- transformation
- transformation rules
- word
- word count
- wordnet
- wordnet sense
- words
