Sixth International Conference on Spoken Language Processing (ICSLP 2000)

Beijing, China
October 16-20, 2000

Interpolation of Stochastic Grammar and Word Bigram Models in Natural Language Understanding

Sven C. Martin, Andreas Kellner, Thomas Portele

Philips Research Labs Aachen, Germany

The paper shows the e ects of combining a stochastic grammar with a word bigram language model by log-linear interpolation. It is divided into three main parts: The first part derives the stochastic grammar model and gives a sound theoretical motivation to incorporate word dependencies such as bigrams. The second part describes two different algorithmic approaches to the combination of both models by log-linear interpolation. The third part reports attribute error rate (AER) results measured on the Philips corpus of train time table inquiries that show a reduction of up to 9% relative.


Full Paper

Bibliographic reference.  Martin, Sven C. / Kellner, Andreas / Portele, Thomas (2000): "Interpolation of stochastic grammar and word bigram models in natural language understanding", In ICSLP-2000, vol.1, 234-237.