Position models and language modeling

Arnaud Zdziobeck (1) , Franck Thollard (1)

1 LHC - Laboratoire Hubert Curien

In statistical language modelling the classic model used is $n$-gram. This model is not able however to capture long term dependencies, \emph{i.e.} dependencies larger than $n$. An alternative to this model is the probabilistic automaton. Unfortunately, it appears that preliminary experiments on the use of this model in language modelling is not yet competitive, partly because it tries to model too long term dependencies. We propose here to improve the use of this model by restricting the dependency to a more reasonable value. Experiments shows an improvement of 45\% reduction in the perplexity obtained on the Wall Street Journal language modeling task.

Domains: Artificial Intelligence [cs.AI]

Arnaud Zdziobeck, Franck Thollard. Position models and language modeling. Structural and Syntactic Pattern Recognition and Statistical Techniques in Pattern Recognition, Dec 2008, Orlando, United States. pp.76-85. ⟨ujm-00322820⟩