Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 5

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Semantic disambiguation in a MT system based on a bilingual dictionary

100%

Jassem K. , Wagner A.

Archives of Acoustics

2007

tom Vol. 32, No. 1

75-87

The paper presents an approach to semantic disambiguation in a transfer MT system based on a bilingual dictionary, i.e. the dictionary built from source-target pairs. The approach assumes building a concept ontology for nouns. The ontological concepts are applied as semantic values in lexical rules for verbs, adjectives and prepositions. A set of "semantic accommodation" rules is developed. The set is consulted during the process of semantic disambiguation that follows syntactical parsing. The approach has been applied in a commercial bi-directional Polish-English MT system called Translatica.

Using regular expressions in translation memories

100%

Gintrowicz J. , Jassem K.

Systems Science

2008

tom Vol. 34, no 4

37-40

The paper presents the idea of using regular expressions in translation systems based on translation memories. Regular expressions (regexps) are used for: search for a match in the input sentence, search for an appropriate example in the translation memory and in the transfer of the input sentence into its equivalent. The application of transfer rules to translation memories supports the thesis, put forward in the paper, that Machine Translation and Computer-Aided Translation converge into the same direction.

A Conceptual ontology for machine translation from/into Polish

100%

Jassem K. , Wagner A.

Archives of Control Sciences

2005

tom Vol. 15, no. 4

567-574

The paper presents a conceptual ontology that has been developed for the purpose of machine translation from and into Polish. The ontology has been applied in Translatica - a general domain MT system that currently translates texts between Polish and English and aims at the development of other language pairs including Polish. The Translatica ontology, designed mainly for disambiguation purposes, contains noun terms. The ontological concepts are applied as semantic values in lexical rules for verbs, adjectives and prepositions. The ontology is based on WordNet. The paper compares the adopted approach to those used in other transfer-based and interlingua-based syustems. It also points out justifies the differences between the Translatica ontology and WordNet.

Machine translation using scarce bilingual corpora

100%

Jassem K. , Kowalski T.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

2007

tom Vol. 11, No 1-2

21-33

We propose a method for automatic extraction of translation rules suitable for a rule-based machine translation system by using a target language syntactic parser and scarce bilingual resources as linguistic knowledge sources. We propose an algorithm that assembles translation rules in order to translate an input sentence.

Linguistic aspects of text normalization in a polish text-to-speech system

80%

Graliński F. , Jassem K. , Wagner A. , Wypych M.

Systems Science

2006

tom Vol. 32, no 4

7-15

The paper addresses linguistic problems of text normalization for the Polish language. Text normalization, which converts the written form of a text into the spoken form, is one of the preprocessing steps in text-to-speech systems. Normalization of texts in analytic languages like English does not necessarily require deep linguistic analysis. However, it is shown here that for synthetic languages, like Polish, linguistic analysis is crucial for the normalization process. Existing Polish text-to-speech systems, even though highly estimated for the naturalness of output, do not solve main normalization problems. The authors’ team aims at developing a text-to-speech system that will include a strong text normalization module. The idea is to design the module using linguistic resources and mechanisms developed for a Machine Translation system, Translatica. Progress of research may be followed at www.poleng.pl, where the user may input a source Polish text in the written form and obtain its "translation" after normalization.