ACL RD-TEC 1.0 Summarization of C00-1009
Paper Title:
COMBINATION OF N-GRAMS AND STOCHASTIC CONTEXT-FREE GRAMMARS FOR LANGUAGE MODELING
COMBINATION OF N-GRAMS AND STOCHASTIC CONTEXT-FREE GRAMMARS FOR LANGUAGE MODELING
Authors: Jose-Miguel Benedi and Joan-Andreu Sanchez
Primarily assigned technology terms:
Other assigned terms:
- approach
- bracketed corpora
- bracketed corpus
- case
- context-free grammars
- convergence
- corpora
- derivation
- derivations
- distribution
- estimation
- froln structural information content
- grammars
- information content
- input string
- interpretation
- labeling
- language model
- language models
- learning problem
- linear combination
- n-gram
- n-gram model
- n-gram models
- n-grams
- nonterminal
- normal form
- penn treebank
- penn treebank project
- perplexity
- probabilistic model
- probability
- probability distributions
- process
- relation
- sentence
- sentences
- sentential form
- speech tag
- statistical information
- stochastic context-free grammars
- structural information
- substring
- symbols
- syntactic structures
- technique
- test corpus
- test set
- time complexity
- training
- training corpus
- training set
- treebank
- treebank corpus
- treebank project
- vocabulary
- vocabulary size
- word
- word distribution
- words
