Search results for " translation."

showing 10 items of 474 documents

Towards the evaluation of automatic simultaneous speech translation from a communicative perspective

2021

In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine…

FOS: Computer and information sciencesComputer Science - Computation and LanguageMachine translationEnd userComputer sciencebusiness.industrymedia_common.quotation_subjectSample (statistics)Context (language use)Intelligibility (communication)computer.software_genreSpeech translationQuality (business)Artificial intelligencebusinessComputation and Language (cs.CL)computerInterpreterNatural language processingmedia_commonProceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
researchProduct

Fast Neural Machine Translation Implementation

2018

This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.

FOS: Computer and information sciencesFocus (computing)Computer Science - Computation and LanguageMachine translationComputer sciencebusiness.industrycomputer.software_genreTrack (rail transport)Softmax functionArtificial intelligenceInference enginebusinesscomputerComputation and Language (cs.CL)
researchProduct

Facilitating terminology translation with target lemma annotations

2021

Most of the recent work on terminology integration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the target language sentence. In day-to-day work of professional translators, however, it is seldom the case as translators work with bilingual glossaries where terms are given in their dictionary forms; finding the right target language form is part of the translation process. We argue that the requirement for apriori specified target language forms is unrealistic and impedes the practical applicability of previous work. In this work, we propose to train machine translation systems using a source-side data augmentatio…

FOS: Computer and information sciencesLemma (mathematics)Computer Science - Computation and LanguageMachine translationProcess (engineering)Computer sciencebusiness.industryLatvianTerm (logic)Translation (geometry)computer.software_genrelanguage.human_languageTerminologylanguageArtificial intelligencebusinessComputation and Language (cs.CL)computerNatural language processingSentence
researchProduct

Ambiguity and complementation in recognizable two-dimensional languages

2008

The theory of one-dimensional (word) languages is well founded and investigated since fifties. From several years, the increasing interest for pattern recognition and image processing motivated the research on two-dimensional or picture languages, and nowadays this is a research field of great interest. A first attempt to formalize the concept of finite state recognizability for two-dimensional languages can be attributed to Blum and Hewitt ([7]) who started in 1967 the study of finite state devices that can define two-dimensional languages, with the aim to finding a counterpart of what regular languages are in one dimension. Since then, many approaches have been presented in the literature…

Finite-state machineTessellationCOMPLEXITYSettore INF/01 - Informaticamedia_common.quotation_subjectPicture LanguageAmbiguityPattern RecognitionPicture languageAlgebraRule-based machine translationRegular languageFormal LanguagePICTURE-LANGUAGES; NONDETERMINISM; COMPLEXITY; AUTOMATAFormal languageRegular expressionAUTOMATAArithmeticPICTURE-LANGUAGESmedia_commonMathematicsNONDETERMINISM
researchProduct

Arnold Zweig - Aufnahme in Polen

2016

Śląski niemieckojęzyczny autor – Arnold Zweig – zajmował się do końca swojego życia traumatycznym okresem I wojny światowej i napisał wiele dzieł poświęconych tej tematyce. Artykuł ten w pierwszej kolejności prezentuje zainteresowanie osobą Arnolda Zweiga w Polskiej Republice Ludowej oraz opisuje recepcję tłumaczeń jego powieści autorstwa nieżyjącej już tłumaczki Wandy Kragen. W drugiej części niniejszej publikacji autorka skupia się na scharakteryzowaniu powieści „Junge Frau von 1914“ (Młoda kobieta z roku 1914).

First World WarI wojna światowaPolska Rzeczpospolita LudowaPolish People’s Republicwar novelstłumaczenia literackieliterary translationsArnold Zweigpowieści wojenne
researchProduct

A dynamic program analysis to find floating-point accuracy problems

2012

Programs using floating-point arithmetic are prone to accuracy problems caused by rounding and catastrophic cancellation. These phenomena provoke bugs that are notoriously hard to track down: the program does not necessarily crash and the results are not necessarily obviously wrong, but often subtly inaccurate. Further use of these values can lead to catastrophic errors.In this paper, we present a dynamic program analysis that supports the programmer in finding accuracy problems. Our analysis uses binary translation to perform every floating-point computation side by side in higher precision. Furthermore, we use a lightweight slicing approach to track the evolution of errors.We evaluate our…

Floating pointComputer engineeringComputer scienceComputationRoundingReal-time computingBinary translationDynamic program analysisBenchmark (computing)ProgrammerProceedings of the 33rd ACM SIGPLAN Conference on Programming Language Design and Implementation
researchProduct

A Polysystemic Study of Folk Literature in Nineteenth-Century Norway

1999

The Norwegian Folktales, collected, transcribed and re-written by Per Christian Asbjørnsen and Jørgen Moe from 1842, had a pivotal role in the shaping of a cultural and linguistic identity in the emerging nation-state. After four centuries of ‘union’ where Denmark and Sweden were the dominant partners, Norway was finally declared an independent nation state in 1914. The folktales, handed down orally through the generations across the country, embodied important symbolical, cultural and linguistic characteristics from the rural environment. The paper describes the context and process through which The Norwegian Folktales influenced both the emerging natonal identity and the emerging Norwegia…

Folktales National Identity Asbjornsen and Moe Oral Narrative Translation Theory Norms Toury
researchProduct

La sufixació apreciativa del català: creacions lèxiques i implicacions morfològiques

2015

Resum: La situació de la derivació apreciativa dins la morfologia és excepcional, perquè la informació limitada que contenen, en general, les gramàtiques i els diccionaris sobre els apreciatius així com l’ús habitual d’aquestes formes en contextos familiars i informals fan que la creativitat dels parlants no es vegi limitada per normatives i que, per tant, aflorin solucions imaginatives, que, tot i la variació existent, segueixen uns condicionaments gramaticals clars. L’objectiu d’aquest treball és aportar noves dades en aquest camp a partir de formes recollides en corpus tradicionals i per internet, amb una doble finalitat: d’una banda, aprofundir en les particularitats morfològiques de la…

Fonologialcsh:Language and LiteratureLinguistics and LanguageFilologíasgènerePhonologyLanguage and LinguisticsKey (music)Catalàlcsh:P1-1091Rule-based machine translationNounInflectionSociologycatalàNeologismCatalan languageLiteratureUNESCO::CIENCIAS DE LAS ARTES Y LAS LETRASNeologismesLingüísticabusiness.industryNew wordsneologismesmarques flexivesflexió nominalderivació apreciativa; neologismes; flexió nominal; marques flexives; gènere; catalàLinguisticslanguage.human_languagelcsh:Philology. Linguisticsderivació apreciativaVariation (linguistics):CIENCIAS DE LAS ARTES Y LAS LETRAS [UNESCO]languagelcsh:PCatalanbusinessCaplletra. Revista Internacional de Filologia
researchProduct

USING FORUM COLLABORATIVE SETTINGS FOR TRANSLATION OUTCOMES: A THREAT TO TRANSLATION PROFESSIONALS?

2018

Translation and transcreation can both be considered as practices carried out by professionals trained in the communication of languages, cultures and situational settings. However, a growing number of internet users resort to the Internet to equip themselves with language knowledge, exploiting the collaborative setting the Internet provides. Online collaboration is based on the new culture of openness and engagement, which is negotiated via interaction with the final aim of providing a possible good, and “professional-like”, translation. As stated by Guyon (2010, 33), coordination and discussion between participants are part and parcel of the translation process. Although fora have thoroug…

Forum translation transcreation collaborationSettore L-LIN/12 - Lingua E Traduzione - Lingua Inglese
researchProduct

Traduir sota la dictadura franquista, traduir clandestinament: Poesia (1944-1945) i Ariel (1946-1951)

2013

After the Spanish Civil War, Francisco Franco’s dictatorship banned Catalan translations for a decade. But in 1948, Carles Riba’s translation of the Odyssey and Josep Maria Sagarra’s translation of the Divine Comedy were published, albeit with severe restrictions. These restrictions remained virtually unchanged until 1962, when the regime began allowing the publication of Catalan translations without prior censorship. In the 1940s, when the repression was at its fiercest, two clandestine journals in Catalan, Poetry (1944-1945) and Ariel (1946-1951), regularly translated a portion of one of the classics of Western literature, and also published contemporary and avant-garde material as well a…

FrancoUNESCO::CIENCIAS DE LAS ARTES Y LAS LETRASAriel:CIENCIAS DE LAS ARTES Y LAS LETRAS [UNESCO]Catalan translationFranquismeTraducción e InterpretaciónPoesiaClandestinitatUnderground publishingClandestine publishingTraducció catalana
researchProduct