Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

9

NAACL
1994

favoriteEmaildiscussreport

107views Computational Linguistics» more NAACL 1994»

Language Modeling with Sentence-Level Mixtures

13 years 5 months ago

Language Modeling with Sentence-Level Mixtures

Download acl.ldc.upenn.edu

Thispaperintroduces a simple mixtare languagemodelthat attempts to capture long distance conslraints in a sentence orparagraph. The model is an m-component mixture of Irigram models. The models were constructed using a 5K vocabulary and trained using a 76 million wordWailStreetJournal textcorpus. Using theBU recognition system, experiments show a 7% improvement in recognition accuracy with themixture trigrammodels ascomparedto using a Irigram model.

Rukmini Iyer, Mari Ostendorf, Jan Robin Rohlicek

Real-time Traffic

Irigram Model | Long Distance Conslraints | NAACL 1994 | NAACL 2007 | Sentence Orparagraph |

claim paper

Related Content

» Sentence level emotion recognition based on decisions from subsentence segments

» Investigating Statistical Techniques for SentenceLevel Event Classification

» Translating from Complex to Simplified Sentences

» Fast exact maximum likelihood estimation for mixture of language model

» CorpusBased Tools for ComputerAssisted Acquisition of Reading Abilities in Cognate Languag...

» Factorized Asymptotic Bayesian Inference for Mixture Modeling

» A Vector Space Model for Subjectivity Classification in Urdu aided by CoTraining

» Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Mode...

» Markov Logic Mixtures of Gaussian Processes Towards Machines Reading Regression Data

Post Info
More Details (n/a)

Added	02 Nov 2010
Updated	02 Nov 2010
Type	Conference
Year	1994
Where	NAACL
Authors	Rukmini Iyer, Mari Ostendorf, Jan Robin Rohlicek

Comments (0)