In this paper, an extension of n-grams is proposed. In this extension, the memory of the model (n) is not fixed a priori. Instead, first, large memories are accepted and afterwards, merging criteria are applied to reduce complexity and to ensure reliable estimations. The results show how the perplexity obtained with x-grams is smaller than that of n-grams. Furthermore, the complexity is smaller than trigrams and can become close to bigrams.
Cite as: Bonafonte, A., Mariño, J.B. (1996) Language modeling using x-grams. Proc. 4th International Conference on Spoken Language Processing (ICSLP 1996), 394-397, doi: 10.21437/ICSLP.1996-76
@inproceedings{bonafonte96_icslp, author={Antonio Bonafonte and José B. Mariño}, title={{Language modeling using x-grams}}, year=1996, booktitle={Proc. 4th International Conference on Spoken Language Processing (ICSLP 1996)}, pages={394--397}, doi={10.21437/ICSLP.1996-76} }