Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Improving N-gram Modeling Using Distance-Related Unit Association Maximum Entropy Language Modeling

Shuwu Zhang (1), Harald Singer (1), Dekai Wu (2), Yoshinori Sagisaka (1)

(1) ATR Interpreting Telecommunication Research Labs. Kyoto, Japan
(2) The HongKong University of Science and Technology, Hong Kong

In this paper, a distance-related unit association maximum entropy (DUAME) language modeling is proposed. This approach can model an event (unit subsequence) using the co-occurrence of full distance unit association (UA) features so that it is able to pursue a functional approximation to higher order N-gram with significantly less memory requirement. A smoothing strategy related to this modeling will also be discussed. Preliminary experimental results have shown that DUAME modeling is comparable to conventional N-gram modeling in perplexity with significantly small number of parameters.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Zhang, Shuwu / Singer, Harald / Wu, Dekai / Sagisaka, Yoshinori (1999): "Improving n-gram modeling using distance-related unit association maximum entropy language modeling", In EUROSPEECH'99, 1611-1614.