ACL RD-TEC 1.0 Summarization of H05-1063
Paper Title:
MINING CONTEXT SPECIFIC SIMILARITY RELATIONSHIPS USING THE WORLD WIDE WEB
MINING CONTEXT SPECIFIC SIMILARITY RELATIONSHIPS USING THE WORLD WIDE WEB
Authors: Dmitri Roussinov and Leon J. Zhao and Weiguo Fan
Primarily assigned technology terms:
- algorithm
- categorization
- clustering
- co-occurrence analysis
- computational linguistics
- cross-language retrieval
- decomposition
- detection and tracking
- disambiguation
- document representation
- document retrieval
- error reduction
- heuristic algorithm
- human language
- human language technology
- indexing
- information management
- information retrieval
- information retrieval tasks
- information systems
- java
- k-means
- language processing
- language technology
- latent semantic indexing
- learning
- learning approach
- local context analysis
- machine learning
- machine learning approach
- mining
- natural language processing
- normalization
- online processing
- processing
- processor
- query expansion
- search
- search engine
- search engines
- semantic indexing
- similarity computation
- singular value decomposition
- splitting
- statistical co-occurrence analysis
- summarization
- term translation
- term weighting
- text categorization
- tf-idf weighting
- topic detection
- topic detection and tracking
- vector expansion
- vector normalization
- vector representation
- vector space model
- web search
- weighting
- word co-occurrence analysis
- world wide web
Other assigned terms:
- ambiguity
- approach
- association for computational linguistics
- case
- cluster
- co-occurrence
- co-occurrence information
- co-occurrences
- corpora
- correlation
- document
- document frequency
- document similarity
- document vectors
- evaluation metric
- evaluation set
- french
- heuristic
- human judgments
- implementation
- interpretation
- latent semantic
- linguistic
- linguistics
- local context
- measure
- natural language
- noise
- ontology
- phrase
- probability
- procedure
- process
- processing time
- queries
- query
- representations
- retrieval task
- scalability
- search results
- semantic
- semantic similarity
- similarity matrix
- similarity measure
- similarity thesaurus
- similarity threshold
- statistics
- stems
- synonyms
- technique
- technology
- term
- terms
- test collection
- test set
- text
- text documents
- theory
- thesaurus
- topics
- training
- user
- user query
- vector space
- vocabulary
- web corpus
- web pages
- word
- word co-occurrence
- words
