ACL RD-TEC 1.0 Summarization of P06-1099
Paper Title:
YOU CAN'T BEAT FREQUENCY (UNLESS YOU USE LINGUISTIC KNOWLEDGE) – A QUALITATIVE EVALUATION OF ASSOCIATION MEASURES FOR COLLOCATION AND TERM EXTRACTION
YOU CAN'T BEAT FREQUENCY (UNLESS YOU USE LINGUISTIC KNOWLEDGE) – A QUALITATIVE EVALUATION OF ASSOCIATION MEASURES FOR COLLOCATION AND TERM EXTRACTION
Authors: Joachim Wermter and Udo Hahn
Primarily assigned technology terms:
- algorithm
- automatic term recognition
- chi-square test
- chunking
- co-occurrence counting
- co-occurrence frequency counting
- collocation extraction
- computational linguistics
- domain-specific automatic term recognition
- frequency counting
- identification
- information retrieval
- lexical processing
- mining
- nlp
- normalization
- parsers
- phrase chunking
- pos tagging
- processing
- qualitative evaluation
- ranking
- re-ranking
- recognition
- shallow syntactic analysis
- significance testing
- statistical nlp
- statistical significance testing
- statistical testing
- syntactic analysis
- taggers
- tagging
- term dioscovery
- term extraction
- term recognition
- terminology
- tomatic term dioscovery
Other assigned terms:
- approach
- association for computational linguistics
- association measure
- break
- co-occurrence
- co-occurrence frequency
- collocation
- corpora
- data set
- data sets
- distribution
- entropy
- fact
- hypothesis
- knowledge
- large text corpora
- lexical association
- lexical material
- likelihood
- linguistic
- linguistic knowledge
- linguistics
- log-likelihood
- measure
- measures
- medline
- mutual information
- n-gram
- newspaper corpus
- noun phrases
- null hypothesis
- occurrence frequency
- phrase
- probability
- slot
- statistical significance
- term
- terms
- text
- text corpora
- textbook
- tokens
- trigram
- umls
