UNIGE document Chapitre d'actes
previous document  unige:3475  next document
add to browser collection
Title

Training Statistical Language Models from Grammar-Generated Data: a Comparative Case-Study

Authors
Hockey, Beth Ann
Christian, Gwen
Published in Proceedings of the GoTAL Conference. Gothenburg (Sweden). 2008
Abstract Statistical language models (SLMs) for speech recognition have the advantage of robustness, and grammar-based models (GLMs) the advantage that they can be built even when little corpus data is available. A known way to attempt to combine these two methodologies is first to create a GLM, and then use that GLM to generate training data for an SLM. It has however been difficult to evaluate the true utility of the idea, since the corpus data used to create the GLM has not in general been explicitly available. We exploit the Open Source Regulus platform, which supports corpus-based construction of linguistically motivated GLMs, to perform a methodologically sound comparison: the same data is used both to create an SLM directly, and also to create a GLM, which is then used to generate data to train an SLM. An evaluation on a medium-vocabulary task showed that the indirect method of constructing the SLM is in fact only marginally better than the direct one. The method used to create the training data is critical, with PCFG generation heavily outscoring CFG generation.
Full text
Proceedings chapter - public document Free access
Structures
Citation
(ISO format)
HOCKEY, Beth Ann, RAYNER, Emmanuel, CHRISTIAN, Gwen. Training Statistical Language Models from Grammar-Generated Data: a Comparative Case-Study. In: Proceedings of the GoTAL Conference. Gothenburg (Sweden). [s.l.] : [s.n.], 2008. https://archive-ouverte.unige.ch/unige:3475

208 hits

87 downloads

Update

Deposited on : 2009-10-02

Export document
Format :
Citation style :