ACL RD-TEC 1.0 Summarization of W02-1032
Paper Title:
EXPLOITING HEADWORD DEPENDENCY AND PREDICTIVE CLUSTERING FOR LANGUAGE MODELING
EXPLOITING HEADWORD DEPENDENCY AND PREDICTIVE CLUSTERING FOR LANGUAGE MODELING
Authors: Jianfeng Gao and Hisami Suzuki and Yang Wen
Primarily assigned technology terms:
- binary branching
- category probability estimation
- clustering
- clustering technique
- computational linguistics
- computing
- decoding
- error rate reduction
- estimator
- german speech recognition
- headword prediction
- identification
- japanese speech recognition
- kana-kanji conversion
- language modeling
- language processing
- likelihood estimation
- maximum entropy
- maximum likelihood
- maximum likelihood estimation
- model estimation
- model parameter estimation
- modeling
- n-best rescoring
- optimization
- parameter estimation
- parameter optimization
- parser
- predictive clustering
- probability estimation
- processing
- rate reduction
- recognition
- rescoring
- smoothing
- smoothing method
- smoothing techniques
- speech recognition
- statistical language modeling
- statistical parser
- word bigram
- word clustering
Other assigned terms:
- ambiguity
- annotated corpus
- asian language
- asian language text
- association for computational linguistics
- backoff
- baseline model
- bigram
- bunsetsu
- case
- character error rate
- characters
- cluster
- clustering model
- clusters
- co-occurrence
- community
- comparative study
- compounds
- conditional probabilities
- conditional probability
- content words
- context window
- corpora
- data sparseness
- data sparseness problem
- dependency relation
- dependency relations
- dependency structure
- derivation
- distribution
- document
- entropy
- error rate
- estimation
- evaluation methodology
- fact
- function word
- function words
- hypotheses
- implementation
- interpolation
- japanese text
- kanji
- knowledge
- language model
- language models
- lexicon
- likelihood
- linguistic
- linguistic structure
- linguistics
- linguists
- local dependency
- mapping
- mapping table
- method
- methodology
- model parameter
- model size
- morpheme
- morpheme boundary
- morphemes
- n-best list
- n-gram
- n-gram model
- n-gram models
- n-grams
- newspaper corpus
- oracle
- orthography
- out-of-vocabulary rate
- part-of-speech
- pcfgs
- penn treebank
- permutation
- perplexity
- phrase
- probabilities
- probability
- probability estimate
- probability estimates
- relation
- scrambling
- semantic
- sentence
- sentences
- sparseness problem
- structural information
- syntactic structure
- tag set
- tags
- technique
- terms
- test corpora
- test data
- text
- training
- training data
- transcript
- tree
- treebank
- trigram
- trigram model
- unigram
- word
- word category
- word category probability
- word dependency
- word order
- word pair
- word sequence
- word string
- word strings
- word trigram
- word trigram model
- words
