ACL RD-TEC 1.0 Summarization of N04-4030
Paper Title:
NEARLY-AUTOMATED METADATA HIERARCHY CREATION
NEARLY-AUTOMATED METADATA HIERARCHY CREATION
Authors: Emilia Soica and Marti A. Hearst
Primarily assigned technology terms:
- algorithm
- automated processing
- automated text categorization
- categorization
- classification
- clustering
- computing
- document clustering
- editing
- information browsing
- information browsing and navigation
- internet
- k-means
- k-means clustering
- learning
- linear regression
- listing
- machine learning
- navigation
- nlp
- processing
- pruning
- regression
- search
- search engine
- supervised text categorization
- terminology
- text categorization
- text categorization algorithm
- translation systems
- unsupervised method
- word space
Other assigned terms:
- approach
- bottom-up approach
- case
- category structure
- classification hierarchy
- cluster
- clusters
- co-occurrence
- co-occurrence statistics
- co-occurrences
- community
- content-oriented metadata
- context vector
- cosine distance
- dictionary
- dictionary definitions
- distribution
- document
- document collection
- document collections
- document set
- hierarchical structure
- hypernym
- implementation
- index
- information gain
- information organization
- information science
- knowledge
- language models
- lexical co-occurrence
- lexical hierarchy
- lexical resource
- meaning
- meanings
- metadata
- method
- modern information science
- nlp applications
- pairs of words
- procedure
- process
- query
- relation
- statistics
- subsumption
- synonym
- synsets
- term
- term co-occurrence
- terms
- test collection
- text
- thesaurus
- topics
- tree
- trees
- usability
- user
- web site
- word
- word senses
- wordnet
- words
