| Institute of Informatics>>> Acta Cybernetica>>> Past Issues>>> Volume 19, Number 2, 2009>>> |
 Magyarul
|
Statistical Language Models within the Algebra of Weighted Rational Languages
Thomas Hanneforth and Kay-Michael Würzner
Abstract (in LaTeX format)
Statistical language models are an important tool in natural language processing. They represent prior knowledge about a certain language which is usually gained from a set of samples called a \emph{corpus}. In this paper, we present a novel way of creating $N$-gram language models using weighted finite automata. The construction of these models is formalised within the algebra underlying weighted finite automata and expressed in terms of weighted rational languages and transductions. Besides the algebra we make use of five special constant weighted transductions which rely only on the alphabet and the model parameter \emph{N}. In addition, we discuss efficient implementations of these transductions in terms of \emph{virtual constructions}.
Kewords: computational linguistics, weighted rational transductions, statistical language modeling, N-gram models, weighted finite-state automata.
Full text
Available electronic editions: PDF.
Note that full text is available only for papers that are at least 3 years old. For more recent papers only the first page of the paper is provided.
BibTeX entry
@article{Hanneforth:2009:ActaCybernetica,author = {Thomas Hanneforth and Kay-Michael W\"{u}rzner},
title = {Statistical Language Models within the Algebra of Weighted Rational Languages},
journal = {Acta Cybernetica},
volume = {19},
number= {2},
pages = {313--356},
year = {2009},
abstract = {Statistical language models are an important tool in natural language processing. They represent prior knowledge about a certain language which is usually gained from a set of samples called a \emph{corpus}. In this paper, we present a novel way of creating $N$-gram language models using weighted finite automata. The construction of these models is formalised within the algebra underlying weighted finite automata and expressed in terms of weighted rational languages and transductions. Besides the algebra we make use of five special constant weighted transductions which rely only on the alphabet and the model parameter \emph{N}. In addition, we discuss efficient implementations of these transductions in terms of \emph{virtual constructions}.},
keywords = {computational linguistics, weighted rational transductions, statistical language modeling, N-gram models, weighted finite-state automata}
}