ACL RD-TEC 1.0 Summarization of W01-0513
Paper Title:
IS KNOWLEDGE-FREE INDUCTION OF MULTIWORD UNIT DICTIONARY HEADWORDS A SOLVED PROBLEM?
IS KNOWLEDGE-FREE INDUCTION OF MULTIWORD UNIT DICTIONARY HEADWORDS A SOLVED PROBLEM?
Authors: Patrick Schone and Daniel Jurafsky
Primarily assigned technology terms:
- algorithm
- approximation
- coupling
- data compression
- databases
- decomposition
- hidden markov
- hidden markov models
- hypothesizing
- induction
- information retrieval
- interfaces
- internet
- latent semantic analysis
- learning
- lexical access
- mwu induction
- optimization
- post-processing
- pruning
- reporting
- rescoring
- scoring
- segmentation
- segmentation process
- semantic analysis
- singular value decomposition
- terminology
- text compression
- tokenizer
- transformation-based learning
- word bigram
Other assigned terms:
- anaphors
- approach
- array
- automata
- bias
- bigram
- case
- collocation
- community
- compositionality
- corpora
- correlation
- correlations
- dictionaries
- dictionary
- distributional information
- document
- electronic form
- evaluations
- fact
- french
- gold standard
- human knowledge
- hypotheses
- information retrieval community
- interpretation
- knowledge
- latent semantic
- lexicon
- likelihood
- linguistic
- linguistic filter
- linguistic resources
- linguistic structure
- machine-readable dictionary
- markov models
- meaning
- meanings
- measure
- measures
- method
- minimum description length
- mutual information
- n-gram
- n-grams
- names
- non-compositionality
- noun phrases
- nouns
- organization names
- orthography
- part of speech
- part of speech tags
- parts of speech
- pointwise mutual information
- precision
- probabilities
- probability
- process
- proper noun
- punctuation
- queries
- query
- semantic
- semantic compositionality
- semantic relationships
- signal
- suffix
- symbol
- symbols
- syntax
- tags
- technique
- terms
- text
- text corpora
- tokens
- word
- word boundaries
- word sequences
- wordnet
- words
- z-score
