This paper describes the text normalization module of a text to speech fully-trainable conversion system and its application to number transcription. The main target is to generate a language independent text normalization module, based on data instead of on expert rules. This paper proposes a general architecture based on statistical machine translation techniques. This proposal is composed of...

In this paper, we propose a web-based bilingual concordancer, DOMCAT 1 , for domain-specific computer assisted translation. Given a multi-word expression as a query, the system involves retrieving sentence pairs from a bilingual corpus, identifying translation equivalents of the query in the sentence pairs (translation spotting) and ranking the retrieved sentence pairs according to the relevanc...

relative to a hereditary torsion theory $tau$ we introduce a dimension for a module $m$, called {em $tau$-rank of} $m$, which coincides with the reduced rank of $m$ whenever $tau$ is the goldie torsion theory. it is shown that the $tau$-rank of $m$ is measured by the length of certain decompositions of the $tau$-injective hull of $m$. moreover, some relations between the $tau$-rank of $m$ and c...

 In this paper, a new homological dimension of modules, copresented dimension, is defined. We study some basic properties of this homological dimension. Some ring extensions are considered, too. For instance, we prove that if $Sgeq R$ is a finite normalizing extension and $S_R$ is a projective module, then for each right $S$-module $M_S$, the copresented dimension of $M_S$ does not exceed the c...

In this paper, we propose structure transformation rules for statistical machine translation which are lexicalized by only function words. Although such rules can be extracted from an aligned parallel corpus simply as original phrase pairs, their structure is hierarchical and thus can be used in a hierarchical translation system. In addition, structure transformation rules can take into account...

This paper describes an architecture of a machine translation system designed primarily for Slavic languages. The architecture is based upon a shallow transfer module and a stochastic ranker. The shallow transfer module helps to resolve the problems, which arise even in the translation of related languages, the stochastic ranker then chooses the best translation out of a set provided by a shall...

In this paper, we reported the evaluation results of our CCLQA system at NTCIR-7 ACLIA. We participated in the English-Japanese (EN-JA) cross-lingual task and the Japanese mono-lingual task. The system consists of a question translation module and a nonfactoid-type Japanese question-answering system. The question translation module was developed for NTCIR-6 CLQA, which is a combination of an of...

The article focuses on experimental researching the strategies, methods and means of reproducing nominative language game in popular scientific discourse. We proceed from understanding games by Ludwig Wittgenstein Johan Huizinga according to which its varieties include both acts nomination translation. research is based neological quasi-terms whose main function not give names objects but induc...

Let $R$ be a commutative ring with identity. A proper submodule $N$ of an $R$-module $M$ is an n-submodule if $rmin N~(rin R, min M)$ with $rnotinsqrt{Ann_R(M)}$, then $min N$. A number of results concerning n-submodules are given. For example, we give other characterizations of n-submodules. Also various properties of n-submodules are considered.