Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "natural language translation" wg kryterium: Temat


Wyświetlanie 1-11 z 11
Tytuł:
Synchronous versions of regulated grammars : generative power and linguistic applications
Autorzy:
Horáček, P.
Meduna, A.
Powiązania:
https://bibliotekanauki.pl/articles/375683.pdf
Data publikacji:
2012
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
regulated grammar
synchronous grammar
generative power
natural language translation
Opis:
This paper introduces the notion of new synchronous grammars as systems consisting of two context-free grammars with linked rules instead of linked nonterminals. Further, synchronous versions of regulated grammars, specifically, matrix grammars and scattered context grammars, are discussed. From a theoretical point of view, this paper discusses the power of these synchronous grammars. It demonstrates the following main results. First, if we synchronize context-free grammars by linking rules, the grammar generates the languages defined by matrix grammars. Second, if we synchronize matrix grammars by linking matrices, the generative power remains unchanged. Third, synchronous scattered context grammars generate the class of recursively enumerable languages. From a more practical viewpoint, this paper presents linguistic application prospects. The focus is on natural language translation between Japanese and English.
Źródło:
Theoretical and Applied Informatics; 2012, 24, 3; 175-190
1896-5334
Pojawia się w:
Theoretical and Applied Informatics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
New Grammar Systems and Their Application Perspectives
Autorzy:
Horáček, Petr
Meduna, Alexander
Powiązania:
https://bibliotekanauki.pl/articles/1373727.pdf
Data publikacji:
2013
Wydawca:
Uniwersytet Jagielloński. Wydawnictwo Uniwersytetu Jagiellońskiego
Tematy:
synchronous grammars
regulated grammars
transducers
computational control
generative power
natural language translation
Opis:
This paper presents new grammar systems that describe transformations of syntactic structures. They represent two approaches: synchronous grammars and transducers. The systems consist of well-known models such as context-free grammars and finite automata. Particular attention is paid to synchronization of regulated grammars. The paper recalls formal definitions of the systems and discusses theoretical results regarding their generative and accepting power. The last part briefly introduces application perspectives in natural language translation, illustrated by examples of Czech-English translation.
Źródło:
Schedae Informaticae; 2013, 22; 47-68
0860-0295
2083-8476
Pojawia się w:
Schedae Informaticae
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Specialized fully automatic machine translation system delivering high quality of translated texts
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/1943201.pdf
Data publikacji:
2009
Wydawca:
Politechnika Gdańska
Tematy:
natural language processing
machine translation
translation patterns
Opis:
The paper concerns machine translation systems that form a discipline of computer science and are aimed at writing computer programs that are able to translate text between natural languages. In the paper the author argues that it is not possible to build a machine translation system that would be able to translate any kind of documents with a sufficiently high quality. Instead, the author proposes a specialized machine translation system the aim of which is to translate financial reports concerning the global currency exchange market – forex. For the purpose of building the above mentioned system, the author has proposed his own machine translation method of translation patterns. The translation patterns allow transferring the translation process from the level of single words to the level of words chunks. The translation patterns play a very important role in the case of such an inflectional language as Polish because they make it possible to choose the correct form of Polish translation of foreign phrases depending whether they perform the verb or object function in the sentence. The high quality of the specialized machine translation system developed by the author was proved with many experiments the results of which are demonstrated in the paper. The quality of translation is so high that the Polish translations of English reports from the global currency exchange market can be published on Web pages without any additional changes. Thus, it is possible to totally eliminate the human translator from the process of translation of texts which are highly stereotypical and oriented to a selected and narrow domain.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2009, 13, 4; 347-354
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The Implementation of the example-based machine translation technique for French-to-Polish automatic translation system
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/1986914.pdf
Data publikacji:
2002
Wydawca:
Politechnika Gdańska
Tematy:
natural language processing
computational linguistics
machine translation
Opis:
High-quality machine translation between human languages has for a long time been an unattainable dream for many computer scientists involved in this fascinating and interdisciplinary field of computer application. The developed quite recently example-based machine translation technique seems to be a serious alternative to the existing automatic translation techniques. In the paper the usage of the example based machine translation technique for the development of system which would be able to translate an unrestricted French text into Polish is proposed. The new approach to the example-based machine translation technique that takes into account the peculiarity of the Polish grammar is developed. The obtained primary results of the development of the proposed system seem to be very promising and appear to be a step made in the right direction towards a fully-automatic high quality French-into-Polish machine translation system for unrestricted text.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2002, 6, 3; 523-544
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Knowledge graphs effectiveness in Neural Machine Translation improvement
Autorzy:
Ahmadnia, Benyamin
Dorr, Bonnie J.
Kordjamshidi, Parisa
Powiązania:
https://bibliotekanauki.pl/articles/1839251.pdf
Data publikacji:
2020
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
natural language processing
neural machine translation
knowledge graph representation
Opis:
Maintaining semantic relations between words during the translation process yields more accurate target-language output from Neural Machine Translation (NMT). Although difficult to achieve from training data alone, it is possible to leverage Knowledge Graphs (KGs) to retain source-language semantic relations in the corresponding target-language translation. The core idea is to use KG entity relations as embedding constraints to improve the mapping from source to target. This paper describes two embedding constraints, both of which employ Entity Linking (EL)—assigning a unique identity to entities—to associate words in training sentences with those in the KG: (1) a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG; and (2) a bilingual embedding constraint that forces entity relations in the source-language to be carried over to the corresponding entities in the target-language translation. The method is evaluated for English-Spanish translation exploiting Freebase as a source of knowledge. Our experimental results demonstrate that exploiting KG information not only decreases the number of unknown words in the translation but also improves translation quality
Źródło:
Computer Science; 2020, 21 (3); 299-318
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An Application of Probabilistic Grammars to Efficient Machne Translation
Autorzy:
Skórzewski, Paweł
Powiązania:
https://bibliotekanauki.pl/articles/1037598.pdf
Data publikacji:
2010-09-15
Wydawca:
Uniwersytet im. Adama Mickiewicza w Poznaniu
Tematy:
a* algorithm
machine translation
natural language parsing
pcfg
probabilistic grammars
Opis:
In this paper we present one of the algorithms used to parse probabilistic context-free grammars: the A* parsing algorithm, which is based on the A* graph search method. We show an example of application of the algorithm in an existing machine translation system. The existing CYK-based parser used in the Translatica system was modified by applying the A* parsing algorithm in order to examine the possibilities of improving its performance. This paper presents the results of applying the A* algorithm with different heuristic functions and their impact on the performance of the parser.
Źródło:
Investigationes Linguisticae; 2010, 21; 90-98
1426-188X
1733-1757
Pojawia się w:
Investigationes Linguisticae
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Swarm algorithms for NLP : the case of limited training data
Autorzy:
Tambouratzis, George
Vassiliou, Marina
Powiązania:
https://bibliotekanauki.pl/articles/1396739.pdf
Data publikacji:
2019
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
particle swarm optimisation
natural language processing
text phrasing
machine translation
Opis:
The present article describes a novel phrasing model which can be used for segmenting sentences of unconstrained text into syntactically-defined phrases. This model is based on the notion of attraction and repulsion forces between adjacent words. Each of these forces is weighed appropriately by system parameters, the values of which are optimised via particle swarm optimisation. This approach is designed to be language-independent and is tested here for different languages. The phrasing model’s performance is assessed per se, by calculating the segmentation accuracy against a golden segmentation. Operational testing also involves integrating the model to a phrase-based Machine Translation (MT) system and measuring the translation quality when the phrasing model is used to segment input text into phrases. Experiments show that the performance of this approach is comparable to other leading segmentation methods and that it exceeds that of baseline systems.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 3; 219-234
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The implementation of the example-based machine translation technique for Norwegian-to-Polish automatic translation system
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/970363.pdf
Data publikacji:
2004
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
przetwarzanie języka naturalnego
lingwistyka komputerowa
tłumaczenie komputerowe
natural language processing
computational linguistics
machine translation
Opis:
High-quality machine translation between human languages has for a long time been an unattainable dream for many computer scientists involved in this fascinating and interdisciplinary field of application of computers. The quite recently developed example-based machine translation technique seems to be a serious alternative to the existing automatic translation techniques. In the paper the usage of the example based machine translation technique for the development, of a system, which would be able to translate an unrestricted Norwegian text into Polish is proposed. The new approach to the example-based machine translation technique that takes into account the peculiarity of the Polish grammar is developed. The obtained primary results of development of the proposed system seem to be very promising and appear to be a step made in the right direction towards a fully-automatic high quality Norwegian-into-Polish machine translation system aimed for an unrestricted text.
Źródło:
Control and Cybernetics; 2004, 33, 2; 357-386
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza możliwości i ograniczeń systemów translacji automatycznej wspomaganej przez człowieka na przykładzie systemu tłumaczącego z języka włoskiego na polski
The analysis of possibilities and frontiers of the human-aided machine translation system on the example of Italian-to-Polish translations system
Autorzy:
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/320407.pdf
Data publikacji:
2006
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
translacja automatyczna
przetwarzanie języka naturalnego
sztuczna inteligencja
machine translation
computational linguistics
natural language processing
Opis:
Translacja automatyczna jest dyscypliną nauki dostarczającą wiedzy o tym, jak programować komputery, aby były one w stanie dokonywać automatycznych przekładów pomiędzy wybranymi językami naturalnymi. Translacja automatyczna była również jedną z pierwszych aplikacji, jakie zostały zaproponowane dla komputerów. Niestety szybko okazało się, że zadanie translacji automatycznej jest znacznie trudniejsze, ale zarazem o wiele ciekawsze z naukowego punktu widzenia, niż pierwotnie sądzono. W artykule omówiono podstawowe przyczyny powodujące, że translacja automatyczna jest zadaniem tak niezwykle trudnym. Omówiono również najbardziej obiecujące kierunki rozwoju systemów translacji automatycznej. W dalszej części artykułu przedstawiono podstawowe koncepcje związane z nowym, zaproponowanym przez autora podejściem do zagadnień translacji automatycznej. Zamieszczone w artykule rozważania zilustrowano na przykładzie eksperymentalnego systemu translacji automatycznej, dokonującego przekładu zdań zapisanych w języku włoskim na polski.
Machine translation is a branch of science that teaches us how to program the computers, so as they were able to translate between different human languages. Machine translation was also one of the first application that was proposed for computers. Nonetheless, it soon appeared that the task of machine translation is much more difficult, but also much more interesting from the scientific point of view, than one had ever thought before. In the paper it is thoroughly explained why machine translation is so extremely hard. The most promising directions of development of machine translation systems are also briefly described. The special attention is paid to machine translation systems that are developed for Polish language. The other part of the paper is devoted to some practical experiments of implementation of human-aided machine translation technique for the system that translates from Italian into Polish. The way in which the system operates is illustrated on numerous examples. Italian language belongs to the group of Romance languages at its main feature is a variety of flexion forms of verbs. In the paper the algorithm for Italian flexion is described and it is illustrated on some examples.
Źródło:
Elektrotechnika i Elektronika; 2006, 25, 1; 10-37
1640-7202
Pojawia się w:
Elektrotechnika i Elektronika
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
O wiele więcej niż Google Translate, czyli komputerowe przetwarzanie języka naturalnego (NLP) w translatoryce i translatologii
Far Beyond Google Translate: Natural Language Processing (NLP) in Translation and Translatology
Autorzy:
Okulska, Inez
Powiązania:
https://bibliotekanauki.pl/articles/912393.pdf
Data publikacji:
2020-06-15
Wydawca:
Uniwersytet im. Adama Mickiewicza w Poznaniu
Tematy:
literary translation
machine learning
big data
natural language processing
theory of translation
computational linguistics
machine translation
przekład literacki
teoria przekładu
przetwarzanie języka naturalnego
lingwistyka komputerowa
przekład maszynowy
uczenie maszynowe
Opis:
Przewrotna jest rola postępu – im więcej technologicznego rozwoju, tym większy udział człowieka – w koncepcji, formułowaniu zadań, interpretacji wyników, nadzorze i korekcie. Hierarchia jest zachowana, człowiek wciąż nieodzowny, ale to nie znaczy, że w pewnych obszarach maszynowy potencjał rzeczywiście nie przewyższa ludzkiego i że nie warto z tej przewagi skorzystać. Przetwarzanie języka naturalnego (NLP) to dziedzina niemłoda, ale w ostatnich latach dzięki rozkwitowi metod uczenia głębokiego (deep learning), mody na maszynowe wnioskowanie (data/knowledge mining) czy nowym sprzętowym interfejsom (m.in. zaawansowane rozpoznawanie obrazu) komputerowa analiza tekstu przeżywa istny renesans. W odniesieniu do translacji przyjęło się mówić i pisać głównie o coraz doskonalszych lub właśnie zupełnie niemożliwych algorytmach dla kolejnych par języków czy coraz większej precyzji samego tłumaczenia. Niniejszy artykuł przedstawia natomiast nieco szersze spektrum procesu tłumaczenia i przygląda się elementom przekładowi towarzyszącym (jak choćby krytyka), w których wykorzystanie metod NLP możeprzynieść nowe, ciekawe wyniki. Wyniki, których ze względu na ograniczoną moc obliczeniową człowiek nie jest w stanie osiągnąć. Omówione zostały takie aspekty jak wektorowa reprezentacja języka, stylometria i jej zastosowania czy analiza wielkich zbiorów danych – wszystko to na potrzeby szeroko rozumianychtranslacji i translatologii.
The more technological development, the greater the participation of the human – in formulating tasks and problems, supervising and improving automated processes and interpreting their outcomes. The hierarchy is preserved, humans are still indispensable, but it does not mean that in certain areas of machinery the potential does not really exceed that of the human and that this advantage is not worth exploiting. Natural language processing (NLP) is not a young field, but in recent years, thanks to the thrive of deep learning methods, data and knowledge mining or new human-machine interfaces, computer text analysis is experiencing a real renaissance. As far as translation is concerned, it is mostly algorithms for machine translation that are being discussed. This article, on the other hand, presents a slightly broader spectrum of the translation process and looks at the accompanying elements (such as criticism) in which the use of NLP methods may bring new and interesting results. Results which, due to limited computing power, humans are unable to achieve. The discussion in the paper covers such aspects as the vector representation of language,stylometry and its application, or the analysis of large data sets – all for the purposes of translation and translatology.
Źródło:
Porównania; 2020, 26, 1; 283-297
1733-165X
Pojawia się w:
Porównania
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Using particle swarm optimization to accurately identify syntactic phrases in free text
Autorzy:
Tambouratzis, G.
Powiązania:
https://bibliotekanauki.pl/articles/91802.pdf
Data publikacji:
2018
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
parsing of natural language
machine translation
syntactically-derived phrasing
particle swarm optimization (PSO)
PSO
parameter optimization
Adaptive PSO
AdPSO
Opis:
The present article reviews the application of Particle Swarm Optimization (PSO) algorithms to optimize a phrasing model, which splits any text into linguistically-motivated phrases. In terms of its functionality, this phrasing model is equivalent to a shallow parser. The phrasing model combines attractive and repulsive forces between neighbouring words in a sentence to determine which segmentation points are required. The extrapolation of phrases in the specific application is aimed towards the automatic translation of unconstrained text from a source language to a target language via a phrase-based system, and thus the phrasing needs to be accurate and consistent to the training data. Experimental results indicate that PSO is effective in optimising the weights of the proposed parser system, using two different variants, namely sPSO and AdPSO. These variants result in statistically significant improvements over earlier phrasing results. An analysis of the experimental results leads to a proposed modification in the PSO algorithm, to prevent the swarm from stagnation, by improving the handling of the velocity component of particles. This modification results in more effective training sequences where the search for new solutions is extended in comparison to the basic PSO algorithm. As a consequence, further improvements are achieved in the accuracy of the phrasing module.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2018, 8, 1; 63-77
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
    Wyświetlanie 1-11 z 11

    Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies