Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 59

Liczba wyników na stronie
first rewind previous Strona / 3 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  machine translation
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 3 next fast forward last
EN
Word sense disambiguation deals with deciding the word’s precise meaning in a certainspecific context. One of the major problems in natural language processing is lexical-semantic ambiguity, where a word has more than one meaning. Disambiguating the senseof polysemous words is the most important task in machine translation. This researchwork aims to design and implement English to Hindi machine translation. The designmethodology addresses improving the speed and accuracy of the machine translation process. The algorithm and modules designed in this research work have been deployed on theHadoop infrastructure, and test cases are designed to check the feasibility and reliabilityof this process. The research work presented describes the methodologies to reduce datatransmission by adding a translation memory component to the framework. The speed ofexecution is increased by replacing the modules in the machine translation process withlightweight modules, which reduces infrastructure and execution time.
PL
Po ponad 60 latach intensywnych badań w dziedzinie przekładu komputerowego to niezwykle trudne zagadnienie można już w zasadzie uznać za w znacznej mierze pomyślnie rozwiązane. Przełomem było pojawienie się kilka lat temu komputerowego translatora DeepL, którego działanie oparte zostało na wykorzystaniu sztucznych sieci neuronowych z uczeniem głębokim. Obecnie system DeepL umożliwia dwukierunkowe tłumaczenie pomiędzy prawie 30 językami i jak dotychczas jest zdecydowanie bezkonkurencyjny.
EN
After more than 60 years of intensive research in the field of computer translation, this extremely difficult issue can now, in principle, be considered largely successfully solved. The breakthrough came a few years ago with the appearance of the computer translator DeepL, whose operation was based on the use of artificial neural networks with deep learning. Currently, the DeepL system enables bi-directional translation between almost 30 languages and is so far unrivalled.
EN
In the age of globalization, translation has tended increasingly necessary in bilingual classrooms. The advancement of technology has provided useful tools for making translation easier and more convenient. The automatic tool “Google translate” is increasingly popular and used in many teaching-learning activities recently. The study provides a comprehensive and new insight into the strengths and weaknesses of Google translate. Through the comparison of machine translation and human translation on the aspects of task response, coherence, lexical resource, grammar and accuracy, it shows that there are some limitations in machine translation. which affects the quality of the translations. However, machine translation still plays an important role in supporting users, in terms of time and economic efficiency. Google Translation is a productive tool to assist individuals in learning and teaching in the field of specialized English-medium-instruction subjects.
EN
Bilingual code-mixed (hybrid) languages have become very popular in India as a result of the spread of technology in the form of television, the Internet, and social media. Due to this increase in the use of code-mixed languages in day-to-day communication, the need for maintaining the integrity of the Indian languages has arisen. As a result of this, a tool named Hinglish to Pure Hindi and English Translator was developed. The tool is capable of translating in three ways; namely, Hinglish into pure Hindi and English, pure Hindi into pure English, and vice versa. The tool has achieved an accuracy of 91% in giving Hindi sentences and of 84% in giving English sentences as output when the input sentences were in Hinglish. The tool has also been compared with another similar tools.
EN
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.
PL
W artykule autorzy przedstawili propozycję systemu wspomagającego przekład należącego do kategorii MAHT (Machine-Aided Human Translation). Na wybranych przykładach omówiono zasady funkcjonowania tego rodzaju systemu dla języka szwedzkiego. Rozważany system może wspomagać prace tłumacza, jak i stanowić pomoc dydaktyczną w nauce języka obcego. Innym obszarem jego potencjalnych zastosowań jest rekonstrukcja i rewitalizacja zagrożonych wymarciem języków.
EN
In the paper we propose a machine translation computer tool that belong to the broader category of MAHT (Machine-Aided Human Translation systems). We present on the basis of selected examples the way of work of such system for the Swedish language. The system can be both used as a tool that facilitates the work of translator and can also constitute a didactic aid which can be very useful for the persons who are learning a foreign language. Another area of potential employment of MAHT is reconstruction and revitalization of endangered languages.
EN
Theoretically, the task of translating from one language to another is still the same as it was only twenty or thirty years ago. In practice, however, the paths that translators take to achieve (more or less) the same results are changing all the time. This is because of changes in the media being worked in and with, as well as the increasingly powerful tools which are there for translators to use. These changes inevitably mean that the training which future translators receive has to be changed and adapted to reflect the changes in the way in which they will have to work, and even to reflect changes in the role of the translator.
EN
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.
EN
Re-speaking is a mechanism for obtaining high-quality subtitles for use in live broadcasts and other public events. Because it relies on humans to perform the actual re-speaking, the task of estimating the quality of the results is non- trivial. Most organizations rely on human effort to perform the actual quality assessment, but purely automatic methods have been developed for other similar problems (like Machine Translation). This paper will try to compare several of these methods: BLEU, EBLEU, NIST, METEOR, METEOR-PL, TER, and RIBES. These will then be matched to the human-derived NER metric, commonly used in re-speaking. The purpose of this paper is to assess whether the above automatic metrics normally used for MT system evaluation can be used in lieu of the manual NER metric to evaluate re-speaking transcripts.
10
Content available Przegląd zastosowań analizy text miningowej
PL
W artykule omówiona została eksploracyjna analiza danych tekstowych ze szczególnym naciskiem na zastosowania analizy text miningowej. We współczesnym świecie istnieje wiele różnych branż biznesowych w których pracownicy stykają się z nadmiarem napływających informacji. Rozwój społeczeństwa informacyjnego oraz technologii informatycznych pociągnął za sobą w sposób naturalny powstanie zautomatyzowanych systemów wspomagających wyszukiwanie i porządkowanie informacji. Techniki text miningu znajdują coraz większe zastosowanie, zaś szeroki przegląd zastosowań wraz ze wskazaniem praktycznym możliwości zastosowania analizy text miningowej został dogłębnie omówiony w artykule.
EN
The article discussed the text mining with particular emphasis on the use of text mining analysis. In the modern world there are many different business industries where workers are in contact with an excess of incoming information. The development of the information society and information technology entailed a natural rise of automated systems to support search and organize information. Text mining techniques are increasingly applied, and a broad overview of applications, together with an indication of the practical possibilities of the use of text mining analysis has been thoroughly discussed in the article.
PL
Niniejszy artykuł jest już piątym z dłuższej serii artykułów poświeconej zagadnieniom opracowywania generatorów struktur gramatycznych dla wybranych języków naturalnych. W artykule opisano koncepcję budowy wielojęzycznego generatora zdań typu SVO. Ponadto przedstawiono ideę wykorzystania języka pośredniczącego przekładu, którego rolę pełni w rozwijanym przez autorów systemie sztuczny język esperanto.
EN
The paper is the fifth of a broader series of articles devoted to the issues of the development of syntactic structures generators for selected natural languages. The paper describes the principles of construction of multilingual SVO sentences generator. Moreover, we present the concepts of using intermediate language in machine translation system for which we propose the artificial Esperanto language.
PL
Artykuł jest szóstym i zarazem ostatnim z dłuższej serii artykułów poświęconej zagadnieniom opracowywania generatorów struktur gramatycznych dla wybranych języków naturalnych. W artykule opisano podstawowe idee związane z zasadami funkcjonowania systemów komputerowego przekładu wspomaganych przez człowieka. Autorzy proponują budowę systemu, za pośrednictwem którego użytkownik może tworzyć poprawne składniowo zdania w języku kontrolowanym, które następnie byłby w sposób automatyczny tłumaczone przez komputer na wybrany język docelowy.
EN
The paper is the sixth and the last of a broader series of articles devoted to the issues of the development of syntactic structures generators for selected natural languages. The paper describes the basic ideas and the way of functioning of Human-Aided Machine Translation (HAMT) systems. The authors propose to build the system by the means of which the user would be able to construct syntactically correct sentences in a controlled language. Then these sentences would be automatically translated by the computer into the target language.
EN
The mathematical model of grammatically augmented ontology was introduced to address this issue. This model was used for grammatical analysis of Ukrainian sentences. Domain specific language named GAODL for description of grammatically augmented ontology was developed. The grammar of the language was defined by means of Xtext extension for Eclipse. The developed language was used as an auxiliary part of the information technology for bidirectional Ukrainian sign language translation.
PL
Tematyka artykułu dotyczy opracowywanego przez autorów systemu komputerowego przekładu wspomaganego przez człowieka. Rozwijany system jest z założenia systemem wielojęzycznym, otwartym zarówno leksykalnie, jak i składniowo, który umożliwia komputerowy przekład pomiędzy parą dowolnie wybranych języków. W artykule skoncentrowano się na zagadnieniach związanych z przekładem zaimków osobowych, proponując w tym względzie oryginalne rozwiązanie.
EN
The topic of the paper is about human aided machine-translation system which is developed by the authors. This machine translation system is a multilingual system based on the concept of an intermediate language. The system is opened both lexically and syntactically and it can translate in both directions between any pair of languages. In the paper we concentrate on the issues related to translation of personal pronouns and we propose an original solution of this problem.
PL
Tematyka artykułu dotyczy opracowywanego przez autorów systemu automatycznego przekładu wspomaganego przez człowieka. Rozwijany system jest z założenia systemem wielojęzycznym, umożliwiającym komputerowy przekład pomiędzy parą dowolnie wybranych języków, co osiągnięto dzięki zastosowaniu koncepcji języka pośredniczącego przekładu. Z kolei odpowiednio wysoka jakość uzyskiwanych przekładów jest gwarantowana poprzez zastosowanie języków kontrolowanych, w których tworzone są przez użytkownika teksty podlegające procesom translatorskim.
EN
The topic of the paper is about human aided machine-translation system which is developed by the authors. This machine translation system is a multilingual system based on a concept of an intermediate language thanks to which it can translate in both directions between any pair of languages. The properly high quality of translation is achieved thanks to controlled languages in which the users of the system composed texts that are to be translated.
PL
Przekład komputerowy jest dziedziną informatyki stosowanej, której głównym celem jest opracowywanie programów komputerowych przeznaczonych do w pełni automatycznego tłumaczenia bądź wspomagania procesu translacji z jednego języka naturalnego na inny. Opracowana w latach 90-tych ubiegłego wieku metoda Example-Base Machine Translation (EBMT) stanowiła zerwanie z tradycyjnymi podejściami opartymi na regułach i wprowadziła tłumaczenie bazujące na analizie bilingwicznych korpusów tekstów. W artykule zamieszczono opis wykorzystania rozważanej metody w celu budowy specjalizowanego systemu komputerowego tłumacza przeznaczonego do automatycznego przekładu komunikatów dotyczącej sytuacji na rynkach kapitałowych.
EN
Machine translation is a discipline of applied computer science whose main purpose is to develop computer programs for the aim of fully automatic or computer-aided translation from one natural language into another. The method of Example-Based Machine Translation (EBMT), which was introduced in the 1990s, changed the traditional approach to the development of machine translation systems that relied mainly on rule-based systems. Further, translation processes based on bilingual corpora were introduced. In the paper we describe an implementation of the example based method for the purpose of development of a specialized machine translation system for automatic translation of reports concerning capital markets.
PL
Tematyka artykułu dotyczy zagadnień związanych z automatyzacją przekładu między językami naturalnymi. Jakość pracy współczesnych systemów komputerowego przekładu pozostawia wciąż bardzo wiele do życzenia. W artykule zamieszczono propozycję działań, które powinny przyczynić się do istotnego podniesienia jakości przekładu komputerowego i pozwolić na jego zbliżenie się do rezultatów pracy człowieka. W artykule zaproponowano przeniesienie procesu translacji z poziomu pojedynczych wyrazów na wyższy poziom wielowyrazowych fraz oraz przedstawiono postulat rozwoju systemów komputerowego przekładu zorientowanych na określone obszary tematyczne tłumaczonych tekstów. Wykazano celowość nałożenia swego rodzaju więzów na język źródłowy przekładu, co w znacznym stopniu powinno przyczynić się do eliminacji wieloznaczności tłumaczonych zdań.
EN
The paper discusses issues of machine translation between natural languages. The quality of contemporary machine translation systems is still relatively low and below users' expectations. In the paper we present some suggestions of activities that could result in raising the quality of machine translation and make it similar to the results of work of human translators. We propose the transfer of the translation process from the level of single words to a higher level of multiword phrases. Further, we postulate to develop machine translation systems that are oriented towards specific thematic areas of translated texts. We also demonstrate that some limitations must be placed upon the source language in order to eliminate the ambiguity of sentences to be translated.
EN
In this second part of the survey, we present the application of weighted extended topdown tree transducers in machine translation, which is the automatic translation of natural language texts. We present several formal properties that are relevant to machine translation and evaluate the weighted extended top-down tree transducer along those criteria. In addition, we demonstrate how to extract rules for an extended top-down tree transducer from existing linguistic data and how to obtain suitable rule weights automatically from similar information. Overall, the aim of the survey is twofold. It should provide a synopsis that illustrates how theory (tree transducers) and practice (machine translation) interact on this particular example. Secondly, it presents a uniform and simplified treatment of the rule extraction and training algorithms that is accessible to the nonexpert. Additional details can be found in the original results that are referenced throughout the text.
19
Content available remote A method of hybrid MT for related languages
EN
The paper introduces a hybrid approach to a very specific field in machine translation - the translation of closely related languages. It mentions previous experiments performed for closely related Scandinavian, Slavic, Turkic and Romanic languages and describes a novel method, a combination of a simple shallow parser of the source language (Czech) combined with a stochastic ranker of (parts of) sentences in the target language (Slovak, Russian, Slovenian). The ranker exploits a simple stochastic model of the target language and its main task is to choose the best translation among those provided by the system. The last section of the paper presents results indicating better translation quality compared to the existing MT system for Czech and Slovak and compares them with the results obtained by the translation from Czech to Russian using the same system.
EN
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.
first rewind previous Strona / 3 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.