Title :
Language modeling using x-grams
Author :
Bonafonte, Antonio ; Marino, José B.
Author_Institution :
Univ. Politecnica de Catalunya, Barcelona, Spain
Abstract :
In this paper, an extension of n-grams, called x-grams, is proposed. In this extension, the memory of the model (n) is not fixed a priori. Instead, large memories are accepted first, and merging criteria are then applied to reduce the 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
Keywords :
computational complexity; computational linguistics; grammars; linguistics; merging; modelling; natural languages; nomograms; probability; bigrams; complexity reduction; grammatical inference; language modeling; large memories; merging criteria; model memory; n-grams; perplexity; probability estimation; reliable estimations; trigrams; x-grams; Automata; Character recognition; Contracts; History; Merging; Out of order; Parameter estimation; Proposals; Speech recognition; Stochastic processes;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607137
