ACL RD-TEC 1.0 Summarization of N04-3001
Paper Title:
COLUMBIA NEWSBLASTER: MULTILINGUAL NEWS SUMMARIZATION ON THE WEB
COLUMBIA NEWSBLASTER: MULTILINGUAL NEWS SUMMARIZATION ON THE WEB
Authors: David Kirk Evans and Judith L. Klavans and Kathleen R. McKeown
Primarily assigned technology terms:
- 10-fold crossvalidation
- article extraction
- character encoding
- classification
- clustering
- crawling
- crossvalidation
- dictionary lookup
- document clustering
- document summarization
- document understanding
- encoding
- full machine translation
- identification
- information retrieval
- internet
- learning
- learning program
- learning techniques
- linking
- machine learning
- machine learning techniques
- machine translation
- machine translation systems
- monitoring
- multi-document summarization
- multi-lingual summarization
- multilingual cluster summarization
- multilingual similarity detection
- multilingual summarization
- navigation
- news browsing
- news summarization
- noun phrase detection
- phrase detection
- query translation
- search
- sentence extraction
- similarity computation
- similarity detection
- similarity-based summarization
- summarization
- summarization system
- summarization systems
- summarizer
- the document understanding
- translation system
- translation systems
Other assigned terms:
- approach
- article extraction module
- characters
- cluster
- clusters
- dictionary
- document
- english sentence
- english text
- frame
- french
- generation
- heuristics
- hypothesis
- information retrieval model
- knowledge
- markup
- method
- multigen summarization system
- multilingual document
- multilingual similarity
- named entity
- noun phrase
- phrase
- phrase level
- precision
- priori
- process
- punctuation
- query
- regular expressions
- retrieval model
- russian
- sentence
- sentence level
- sentences
- summarization component
- summarization model
- technique
- terms
- text
- topic structure
- topics
- training
- training data
- training set
- understanding
- user
- web page
- web pages