Search results for "Machine translation"

showing 10 items of 64 documents

Risks in neural machine translation

2020

Abstract The new paradigm of neural machine translation is leading to profound changes in the translation industry. Surprisingly good results have led to high expectations; however, there are substantial risks that have not yet been sufficiently taken into account. Risks exist on three levels: first, what kind of damage can clients and end users incur in safety-critical domains if the NMT result contains errors; second, who is liable for damage caused by the use of NMT; third, what cyber risks can the use of NMT entail, especially when free online engines are used. When establishing sustainable measures to reduce such risks, we also need to consider general principles of human behaviour if …

050101 languages & linguisticsLinguistics and LanguageLiterature and Literary TheoryMachine translationEnd userComputer scienceCommunication05 social sciences02 engineering and technologycomputer.software_genreLanguage and LinguisticsRisk analysis (engineering)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processing0501 psychology and cognitive sciencescomputerLanguage industryFair MT
researchProduct

K-Translate - Interactive Multi-system Machine Translation

2016

The tool described in this article has been designed to help machine translation (MT) researchers to combine and evaluate various MT engine outputs through a web-based graphical user interface using syntactic analysis and language modelling. The tool supports user provided translations as well as translations from popular online MT system application program interfaces (APIs). The selection of the best translation hypothesis is done by calculating the perplexity for each hypothesis. The evaluation panel provides sentence tree graphs and chunk statistics. The result is a syntax-based multi-system translation tool that shows an improvement of BLEU scores compared to the best individual baseli…

PerplexityParsingMachine translationComputer sciencebusiness.industryHybrid machine translationTransfer-based machine translationcomputer.software_genreExample-based machine translationComputer-assisted translationArtificial intelligenceComputational linguisticsbusinesscomputerNatural language processing
researchProduct

Structural Knowledge Extraction from Mobility Data

2016

Knowledge extraction has traditionally represented one of the most interesting challenges in AI; in recent years, however, the availability of large collections of data has increased the awareness that “measuring” does not seamlessly translate into “understanding”, and that more data does not entail more knowledge. We propose here a formulation of knowledge extraction in terms of Grammatical Inference (GI), an inductive process able to select the best grammar consistent with the samples. The aim is to let models emerge from data themselves, while inference is turned into a search problem in the space of consistent grammars, induced by samples, given proper generalization operators. We will …

Process (engineering)Computer scienceGeneralizationmedia_common.quotation_subjectInference02 engineering and technologyMachine learningcomputer.software_genreTheoretical Computer ScienceGrammatical inferenceKnowledge extractionRule-based machine translation020204 information systems0202 electrical engineering electronic engineering information engineeringSearch problemmedia_commonStructural knowledgeGrammarbusiness.industryMobility dataComputer Science (all)020207 software engineeringGrammar inductionArtificial intelligencebusinesscomputerNatural language processing
researchProduct

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

Why Translation Is Difficult

2017

The paper develops a definition of translation literality that is based on the syntactic and semantic similarity of the source and the target texts. We provide theoretical and empirical evidence that absolute literal translations are easy to produce. Based on a multilingual corpus of alternative translations we investigate the effects of cross-lingual syntactic and semantic distance on translation production times and find that non-literality makes from-scratch translation and post-editing difficult. We show that statistical machine translation systems encounter even more difficulties with non-literality.

Linguistics and LanguageTranslationStatistical machine translationMachine translationComputer science02 engineering and technologycomputer.software_genreMachine translation software usability050105 experimental psychologyLanguage and LinguisticsExample-based machine translationRule-based machine translation0202 electrical engineering electronic engineering information engineeringPost-editing0501 psychology and cognitive sciencesDynamic and formal equivalencebusiness.industryCommunication05 social sciencesTransfer-based machine translationLinguisticsNon-literalityComputer-assisted translation020201 artificial intelligence & image processingSynchronous context-free grammarArtificial intelligencebusinesscomputerNatural language processingHermes
researchProduct

Particle Swarm Optimization as a New Measure of Machine Translation Efficiency

2018

The present work proposes a new approach to measuring efficiency of evolutionary algorithm-based Machine Translation. We implement some attributes of evolutionary algorithms performing cosine similarity objective function of a Particle Swarm Optimization (PSO) algorithm then, we evaluate an English text set for translation precision into the Spanish text as a simulated benchmark, and explore the backward process. Our results show that PSO algorithm can be used for translation of multiple language sentences with one identifier only, in other words the technology presented is language-pair independent. Specifically, we indicate that our cosine similarity objective function improves the veloci…

Machine translationComputer scienceComputer Science::Neural and Evolutionary ComputationCosine similarityEvolutionary algorithmParticle swarm optimizationComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)020206 networking & telecommunications02 engineering and technologyTranslation (geometry)computer.software_genreEvolutionary algorithmsSet (abstract data type)IdentifierMachine Translation0202 electrical engineering electronic engineering information engineeringBenchmark (computing)020201 artificial intelligence & image processingCosine similarityAlgorithmcomputer
researchProduct

Natural Language Inference in Ordinary and Support Verb Constructions

2020

The family of clause types known as 'support (or 'light') verb construction' (SVC) manifests a peculiar syntax-semantics interface if compared with ordinary verb constructions (OVC). If, in e.g. She laughed, the verb licenses an argument and assigns it a semantic role, syntacticians of every stripe nowadays agree that it is the noun laugh, in She gave a laugh, which fulfils the same function. The differences between the two types have been extensively discussed in the linguistics literature (systematic research started in the 1970s), less so in Computational Linguistics. This paper has two objectives. First, it will propose an innovative type of semantic role, which is termed Cognate Semant…

Non-verbal predicates Semantic roles Entailments Paraphrasing.Machine translationComputer scienceVerbNotationcomputer.software_genreLinguisticsPredicate (grammar)Settore L-LIN/01 - Glottologia E LinguisticaNounCognateArgument (linguistics)Computational linguisticscomputer
researchProduct

Literāru tekstu mašīntulkojumu un cilvēka tulkojumu no franču un angļu valodas latviešu valodā salīdzinošā analīze

2018

Mašīntulkošanas ietekme tulkošanas jomā ir krietni pieaugusi, taču literāru tekstu tulkošanā tā tiek izmantota reti to sarežģītības dēļ. Šī maģistra darba mērķis ir salīdzināt literāru tekstu mašīntulkojumus ar cilvēka tulkojumiem un analizēt, kāda varētu būt tās iespējamā loma šajā tulkošanas apakšnozarē. Šī darba praktiskajā daļā romānu fragmentu mašīntulkojumi tika salīdzināti ar cilvēku tulkotiem tekstiem divos valodu pāros. Tekstu kvalitāte tika novērtēta, izmantojot manuālu lingvistisko, kā arī automātisko metodi. Kaut gan morfoloģiskās tipoloģijas ziņā angļu valoda un latviešu valoda ir savstarpēji attālinātākas, iegūtie rezultāti liecināja, ka sniegums bija labāks, nekā tulkojot no …

literary translationcomparative analysisValodniecībatranslation technologieslanguage typologymachine translation
researchProduct

Current communication technologies in language processing

2015

Even the most cutting-edge communication-mediated technology like satellite navigation for orbit positioning, pedestrian movement recognition systems based on inertial sensors, 5G systems, let alone medical devices for coordination of human organs functionality would not be invented without technologies for language processing as an information source between humans and communication systems. Regardless of the way we communicate that is via emails, website short tweets, video conferencing systems, social networking, blogs, instant messaging through websites or mobile applications, or texting only, we use a language that is processed by computer system. Thus, the keynote paper discusses lang…

Natural language user interfaceMultimediabusiness.industryComputer scienceLanguage Processingcomputer.software_genreComputer-Mediated CommunicationLanguage and Communication TechnologiesComputational LinguisticsUniversal Networking LanguageMachine TranslationIntelligent Information SystemsLanguage technologyInformation RetrievalQuestion answeringArtificial intelligenceComputational linguisticsbusinessLanguage industrycomputerNatural languageNatural language processing
researchProduct

Data Augmentation for Pipeline-Based Speech Translation

2020

International audience; Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper, we propose two methods for parallel data augmentation for pipeline-based speech translation system development. The first method utilises a speech processing workflow to introduce errors and the second method generates commonly found suffix errors using a rule-based method. We show that the methods in combination allow significantly improving speech translation quality by 1.87 BLEU points over a baseline system.

Machine translationComputer sciencePipeline (computing)media_common.quotation_subjectSpeech recognition[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]speech translationSpeech processingcomputer.software_genreneural machine translation[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]robustness to errorsWorkflow[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG][INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]Speech translationQuality (business)Noise (video)Suffixcomputermedia_commonHuman Language Technologies – The Baltic Perspective - Proceedings of the Ninth International Conference Baltic HLT 2020
researchProduct