Relevant bibliographies by topics / DeepL Translator

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'DeepL Translator'

Author: Grafiati
Published: 4 June 2021
Last updated: 3 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'DeepL Translator.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "DeepL Translator"

1

Ziganshina, Liliya Eugenevna, Ekaterina V. Yudina, Azat I. Gabdrakhmanov, and Juliane Ried. "Assessing Human Post-Editing Efforts to Compare the Performance of Three Machine Translation Engines for English to Russian Translation of Cochrane Plain Language Health Information: Results of a Randomised Comparison." Informatics 8, no. 1 (February 10, 2021): 9. http://dx.doi.org/10.3390/informatics8010009.

Full text
Abstract:
Cochrane produces independent research to improve healthcare decisions. It translates its research summaries into different languages to enable wider access, relying largely on volunteers. Machine translation (MT) could facilitate efficiency in Cochrane’s low-resource environment. We compared three off-the-shelf machine translation engines (MTEs)—DeepL, Google Translate and Microsoft Translator—for Russian translations of Cochrane plain language summaries (PLSs) by assessing the quantitative human post-editing effort within an established translation workflow and quality assurance process. 30 PLSs each were pre-translated with one of the three MTEs. Ten volunteer translators post-edited nine randomly assigned PLSs each—three per MTE—in their usual translation system, Memsource. Two editors performed a second editing step. Memsource’s Machine Translation Quality Estimation (MTQE) feature provided an artificial intelligence (AI)-powered estimate of how much editing would be required for each PLS, and the analysis feature calculated the amount of human editing after each editing step. Google Translate performed the best with highest average quality estimates for its initial MT output, and the lowest amount of human post-editing. DeepL performed slightly worse, and Microsoft Translator worst. Future developments in MT research and the associated industry may change our results.
APA, Harvard, Vancouver, ISO, and other styles
2

Handzel, Zbigniew. "TRANSLATOR DeepL – PRZEŁOM W TŁUMACZENIU KOMPUTEROWYM." ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA 1, no. 6 (June 30, 2021): 22–24. http://dx.doi.org/10.15199/13.2021.6.3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Bowker, Lynne. "Machine translation and author keywords: A viable search strategy for scholars with limited English proficiency?" Advances in Classification Research Online 29, no. 1 (June 28, 2019): 13. http://dx.doi.org/10.7152/acro.v29i1.15455.

Full text
Abstract:
Author keywords are valuable for indexing articles and for information retrieval (IR). Most scientific literature is published in English. Can machine translation (MT) help researchers with limited English proficiency to search for information? We used two MT systems (Google Translate, DeepL Translator) to translate into English 71 Spanish keywords and 43 French keywords from articles in the domain of Library and Information Science. We then used the English translations to search the Library, Information Science and Technology Abstracts (LISTA) database. Half of the translated keywords returned relevant results. Of the half that did not, 34% were well translated but did not align with LISTA descriptors. Translation-related problems stemming from orthographic variation, synonymy, differing syntactic preferences, and semantic field coverage interfered with IR in just 16% of cases. Some of the MT errors are relatively “predictable” and if knowledge organization systems could be augmented to deal with them, then MT may prove even more useful for searching.
APA, Harvard, Vancouver, ISO, and other styles
4

WIESMANN, Eva. "MACHINE TRANSLATION IN THE FIELD OF LAW: A STUDY OF THE TRANSLATION OF ITALIAN LEGAL TEXTS INTO GERMAN." Comparative Legilinguistics 37 (October 23, 2019): 117–53. http://dx.doi.org/10.14746/cl.2019.37.4.

Full text
Abstract:
With the advent of the neural paradigm, machine translation has made another leap in quality. As a result, its use by trainee translators has increased considerably, which cannot be disregarded in translation pedagogy. However, since legal texts have features that pose major challenges to machine translation, the question arises as to what extent machine translation is now capable of translating legal texts or at least certain types of legal text into another legal language well enough so that the post-editing effort is limited, and, consequently, whether a targeted use in translation pedagogy can be considered. In order to answer this question, DeepL Translator, a machine translation system, and MateCat, a CAT system that integrates machine translation, were tested. The test, undertaken at different times and without specific translation memories, provided for the translation of several legal texts of different types utilising both systems, and was followed by systematisation of errors and evaluation of translation results. The evaluation was carried out according to the following criteria: 1) comprehensibility and meaningfulness of the target text; and 2) correspondence between source and target text in consideration of the specific translation situation. Overall, the results are considered insufficient to give post-editing of machine-translated legal texts a bigger place in translation pedagogy. As the evaluation of the correspondence between source and target text was fundamentally worse than with regard to the meaningfulness of the target text, translation pedagogy should respond by raising awareness about differences between machine translation output and human translation in this field, and by improving translation approach and strengthening legal expertise.
APA, Harvard, Vancouver, ISO, and other styles
5

Yang, Yichen. "From speakability to hypothetical mise en scène: A Chinese rendition of monologues from Peter Shaffer’s Amadeus from page to stage." Journal of Adaptation in Film & Performance 13, no. 1 (March 1, 2020): 79–90. http://dx.doi.org/10.1386/jafp_00014_1.

Full text
Abstract:
In order to develop a deeper understanding of speakability and its connection to the actual practice of stage translation, this study explores the rendition of Salieris monologues in the 1986 Beijing production of Peter Shaffers Amadeus. The study finds that speakability does not manifest itself in specific stylistic forms; nor would it be determined by the adoption of any particular translation strategy. Rather, its conceptualization could be deeply embedded in the translators reading of the given dramatic roles and circumstances. This would make the translated playtext a so-called hypothetical performance text incorporated with the translators own hypothetical mise en scne. The process of testing speakability through the actors verbalization is also one where the translators hypothetical mise en scne is evaluated. By tracking the verbal changes made from page to stage, this study shows how the process could be influenced by the negotiation with and between the translational and the theatrical norms governing the different phases of the production, and how a stage translator could make greater contribution to the process.
APA, Harvard, Vancouver, ISO, and other styles
6

Roberts, Trask. "Samuel Beckett's Disruptive Translations of ‘je voudrais que mon amour meure’." Journal of Beckett Studies 28, no. 2 (September 2019): 163–78. http://dx.doi.org/10.3366/jobs.2019.0266.

Full text
Abstract:
Self-translators are often granted freedoms in their translations unimaginable for standard translators. Whereas a standard translation usually prizes sameness (or invisibility as Lawrence Venuti argues), the self-translator may instead highlight difference or disruption. A burgeoning subfield of criticism has outlined the ways in which one of the most famous of these self-translators, Samuel Beckett, makes use of his role as translator to further the reach of his work beyond the constraints of a monolingual text. Whereas most of this criticism has taken aim at Beckett's prose and theater, this essay asks what can be gleaned about Beckett's translation style from his early poetry. Here I focus on Beckett's four-line, untitled poem which begins ‘je voudrais que mon amour meure’ (‘I would like my love to die’). Originally published in 1948 in the bilingual journal Transition Forty-eight, this poem would go on to be edited, translated, reedited, and retranslated over the course of nearly thirty years. The various iterations and translations of the poem are not always harmonious and instead force the reader to consider more deeply the themes of the poem and to question the role of translation. I read the poem in light of Beckett's 1934 essay ‘Recent Irish Poetry’ as well as consider it in response to W.B. Yeats' 1899 poem ‘He Wishes His Beloved Were Dead’. By situating the poem in this context, I argue that this poem is a manifestation of Beckett's argument in the essay that poetry must take into account the division between poet and object. His short poem demonstrates this division as well as that between original and translation and thus allows us a window onto his translation project at large. Considering Beckett's poetic translation permits us to consider how a complementarity of intention towards language does not necessarily entail complementary translations.
APA, Harvard, Vancouver, ISO, and other styles
7

R. Welch, Ellen. "Translating Authority: Cervantes’ Los trabajos de Persiles y Sigismunda in French (1618)." Translation and Literature 19, no. 1 (March 2010): 26–41. http://dx.doi.org/10.3366/e0968136109000752.

Full text
Abstract:
This article examines the creative manipulation of translation theorizing and practice in Vital d'Audiguier's French version of the Persiles. In paratexts, in episodes of the novel that represent France and Spain, and in interjections by Cervantes' fictional translator-narrator, the French translator fashions himself as a figure of authority, posing a bold challenge to Cervantes' own prestige. Latching on to the structures of fictional translation already present in the original novel, d'Audiguier depicts himself as the ‘corrector’ of the Spanish master and ‘author’ of a more perfect text in French than could ever have been possible in the original Castilian. D'Audiguier's work reflects the deep contradictions in seventeenth-century thinking about translation, and indicates the purposes for which individual translators exploited them.
APA, Harvard, Vancouver, ISO, and other styles
8

Ethelb, Hamza. "Hidden Hands: An Institutional Force in Political News Translation." Journal of Critical Studies in Language and Literature 1, no. 1 (May 20, 2020): 1–8. http://dx.doi.org/10.46809/jcsll.v1i1.1.

Full text
Abstract:
This article explores translation in news institutions. While being heavily relied on by media organizations, translation is rarely acknowledged. Translation is deeply interwoven with news in that it is used to employ ideological tendencies and political agendas. This study investigates the powerful role of media institution as a force that intervenes in producing news reports. It uses a questionnaire and interviews to see the influence of editors in the translation of news texts. For this purpose, the views of 21 news translators, journalists and news were surveyed to infer the role of institutions in translation. The study looks at this role from different angles including translator training, instructions given to translators, textual alterations, and policies of news institutions. The findings indicate that intervention by the editors and producers on translation is taking place. The interview participants tend to agree with the intervention of the institution. The questionnaire respondents agree with the statement that translators are given instructions to use specific terminology but disagree with a statement that they have to comply with the policies of the institution.
APA, Harvard, Vancouver, ISO, and other styles
9

Munip, Abdul. "UNIQUENESS IN TRANSLATING ARABIC HAGIOGRAPHY OF SHAIKH ‘ABD AL-QĀDIR AL-JAILĀNĪ: THE CASE OF AN-NŪR AL-BURHĀNĪ." Indonesian Journal of Applied Linguistics 7, no. 3 (January 31, 2018): 668. http://dx.doi.org/10.17509/ijal.v7i3.9817.

Full text
Abstract:
In Indonesia, the hagiographical book of Shaikh ʻAbd al-Qādir al-Jailānī has many versions of translation. One of it is an-Nūr al-burhānī, a Javanese translation by Kyai Muslih al-Marāqī. Unlike other Javanese translations, an-Nūr al-burhānī is not merely a translation but can be considered a new book, in which the translator added some new information and opinion in it. Therefore, the book is interesting to be investigated deeply to find scientific information about the content of the book, the technique, method, and ideology of translation that are adopted and applied by the translator. Using content analysis, the study finds that the book consists of al-Jailānī’s journey of life, his miracles and teachings. The other findings prove that the translator has implemented various techniques of translation such as calque, borrowing, description, amplification-addition, and adaptation techniques. The translator has tried to make the TT (Target Text) easy to be understood by Javanese people, but he tends to apply literal (linguistic transcodification) method rather than interpretative-communicative (translation of the sense) method. As a result, the TT is still influenced by the structure of Arabic as SL (Source Text) and not natural in everyday use of Javanese language. Thus, it can be inferred that the translator more dominantly adopts the ideology of foreignization than domestication. However, what the translator does is more advanced than the other Javanese translators, who usually use only the word for word or literal translation method. This is the uniqueness in translating al-Jailānī’s hagiography or manāqib.
APA, Harvard, Vancouver, ISO, and other styles
10

Antonova, Anna. "Three Faces of the Monster: Interpreting Disability and Creating Meaning in Translations of Alice Munro’s “Child’s Play”." TranscUlturAl: A Journal of Translation and Cultural Studies 11, no. 1 (August 6, 2019): 85–103. http://dx.doi.org/10.21992/tc29400.

Full text
Abstract:
This article addresses the problematics of creating meaning in literary translation by comparing three versions of Alice Munro’s short story “Child’s Play” translated into German, Ukrainian, and Russian. Proceeding from a fluid and unstable source text that represents the conflict of socially perpetuated normative thinking and non-conforming “monstrous” bodies marked by intellectual disability, the translators renegotiate the meaning of embodied otherness and its stigmatization in society in unique ways that reflect their personal perspectives on translation and individual agendas in their translation projects. Munro’s focus on the relationship between a special needs girl and the narrator responsible for her death exposes the society’s deeply ingrained aversion, fear, and hate against people with intellectual disabilities. These prejudiced views find their expression in equating “special” bodies with passive objects, repulsive animal-like creatures, and wild monsters. However, this metaphorical language reflects first and foremost on the narrator, whose hateful speech, breaking through the surface of her seemingly impartial account, unmasks the true faces of the victim and the perpetrator. Each translator ascribes a different meaning to Munro’s deliberately ambiguous narrative: while the German version accentuates the original’s insistence on complexity and uncertainty, the Ukrainian translation increases intensity of the protagonist’s emotional involvement bringing her hatred and disgust to the extreme to make a point about social marginalization of the vulnerable other. The Russian text, conversely, rationalizes the narrator’s actions and turns her tale into a deeply tragic personal confession to align it with a typical plotline of the Russian literary tradition. Overall, three target-language versions of the story add new dimensions to the original text and further destabilize it by consolidating their preferred readings in their treatment of the socially constructed opposition between “monstrous” and “normal”.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "DeepL Translator"

1

Marcassoli, Giulia. "Gli output dei sistemi di traduzione automatica neurale: valutazione della qualità di Google Translate e DeepL Translator nella combinazione tedesco-italiano." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19536/.

Full text
Abstract:
MT is becoming a powerful tool for professional translators, language service providers and common users. The present work focuses on its quality, evaluating the translations produced by two neural MT systems – i.e. Google Translate and DeepL Translator – through manual error annotation. The data set used for this task is composed of semi-specialized German texts translated into Italian. Aim of the present work is to assess the quality of MT outputs for the data set considered and obtain a detailed overview of the type of errors made by the two neural MT systems examined. The first part of this work provides a theoretical background for MT and its evaluation. Chapter 1 deals with the definition of MT and summarizes its history. Moreover, a detailed analysis of the different MT architectures is provided, as well as an overview of the possible application scenarios and the different categories of users. Chapter 2 introduces the notion of quality in the translation field and the main automatic and manual methods applied to MT quality assessment tasks. A comprehensive analysis of some of the most significant studies on neural and phrase-based MT systems output quality is then provided. The second part of this work presents a quality assessment of the output produced by two neural MT systems, i.e. Google Translation and DeepL Translator. The evaluation was performed through manual error annotation based on a fine-grained error taxonomy. Chapter 3 outlines the methodology followed during the evaluation, with a description of the dataset, the neural MT systems chosen for the study, the annotation tool and the taxonomy used during the annotation task. Chapter 4 provides the results of the evaluation and a comment thereof, offering examples extracted from the annotated data set. The final part of this work summarizes the major findings of the present contribution. Results are then discussed, with a focus on their implication for future work.
APA, Harvard, Vancouver, ISO, and other styles
2

Luccioli, Alessandra. "Stereotipi di genere e traduzione automatica dall'inglese all’italiano: uno studio di caso sul femminile nelle professioni." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20408/.

Full text
Abstract:
La presente tesi si pone come obiettivo quello di indagare il rapporto tra stereotipi di genere e traduzione automatica, proponendo uno studio di caso composto da frasi contenenti dei sostantivi riferiti a professioni tradotti automaticamente dall’inglese all’italiano. Il capitolo I offre una panoramica teorica sulla traduzione automatica, per poi approfondire il tema degli stereotipi di genere nella traduzione automatica. Il capitolo II si concentra invece sul rapporto tra genere e lingua, partendo dalla definizione di stereotipi e pregiudizi per passare poi alla questione dei femminili professionali. Vengono delineati gli aspetti linguistici per poi fornire una breve panoramica delle iniziative che sono state proposte nel contesto italiano e internazionale per promuovere l’uso del genere femminile nella lingua ed evitare di usarla in maniera sessista e non inclusiva. Nel capitolo III, dopo aver esposto nel dettaglio la metodologia impiegata degli studi precedenti, si presenta la struttura frasale ideata per condurre lo studio di caso. Partendo dall’elaborazione dei dati statistici sul numero di donne per ogni occupazione, si giunge alla selezione delle professioni da impiegare nello studio. Vengono inoltre illustrati gli strumenti utilizzati nell’analisi basata su corpora che verrà condotta nel capitolo IV, dove si presenta l’analisi degli output forniti da due sistemi di traduzione automatica, DeepL e Google Translate, nella combinazione linguistica inglese-italiano. L’analisi dettagliata di tutti gli aspetti della struttura frasale è corredata da tabelle e grafici esplicativi, inoltre sono presenti approfondimenti sulle traduzioni di alcune professioni di particolare rilevanza. I risultati dell’analisi verranno infine discussi in maniera approfondita, ipotizzando infine le prospettive future degli studi in questo ambito.
APA, Harvard, Vancouver, ISO, and other styles
3

Cozza, Antonella. "Google Translate e DeepL: la traduzione automatica in ambito turistico." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019.

Find full text
Abstract:
Il presente elaborato ha come scopo quello di analizzare il comportamento dei due traduttori automatici più utilizzati attualmente, Google Translate e DeepL, sulla base di testi pertinenti all'ambito turistico, nello specifico, le recensioni di strutture alberghiere. Dopo un breve inquadramento teorico sulla traduzione automatica e sulle principali caratteristiche dei TA sopra citati, si passerà a un esperimento di traduzione dallo spagnolo all'italiano che li coinvolgerà in maniera diretta prendendo in considerazione tre diverse tipologie di recensione. Nel secondo capitolo, verranno valutate le proposte di traduzione offerte da Google Translate e DeepL in base a problemi linguistici, testuali, extralinguistici, di intenzionalità e pragmatici sorti durante l’esperimento. A seguito di ciò, il terzo capitolo e le conclusioni finali si focalizzeranno sui limiti che compromettono maggiormente le prestazioni dei TA, prendendo come riferimento il linguaggio e le caratteristiche proprie dei testi turistici.
APA, Harvard, Vancouver, ISO, and other styles
4

Di, Gangi Mattia Antonino. "Neural Speech Translation: From Neural Machine Translation to Direct Speech Translation." Doctoral thesis, Università degli studi di Trento, 2020. http://hdl.handle.net/11572/259137.

Full text
Abstract:
Sequence-to-sequence learning led to significant improvements to machine translation (MT) and automatic speech recognition (ASR) systems. These advancements were first reflected in spoken language translation (SLT) when using a cascade of (at least) ASR and MT with the new "neural" models, then by using sequence-to-sequence learning to directly translate the input audio speech into text in the target language. In this thesis we cover both approaches to the SLT task. First, we show the limits of NMT in terms of robustness to input errors when compared to the previous phrase-based state of the art. We then focus on the NMT component to achieve better translation quality with higher computational efficiency by using a network based on weakly-recurrent units. Our last work involving a cascade explores the effects on the NMT robustness when adding automatic transcripts to the training data. In order to move to the direct speech-to-text approach, we introduce MuST-C, the largest multilingual SLT corpus for training direct translation systems. MuST-C increases significantly the size of publicly available data for this task as well as their language coverage. With such availability of data, we adapted the Transformer architecture to the SLT task for its computational efficiency . Our adaptation, which we call S-Transformer, is meant to better model the audio input, and with it we set a new state of the art for MuST-C. Building on these positive results, we finally use S-Transformer with different data applications: i) one-to-many multilingual translation by training it on MuST-C; ii participation to the IWSLT 19 shared task with data augmentation; and iii) instance-based adaptation for using the training data at test time. The results in this thesis show a steady quality improvement in direct SLT. Our hope is that the presented resources and technological solutions will increase its adoption in the near future, so to make multilingual information access easier in a globalized world.
APA, Harvard, Vancouver, ISO, and other styles
5

Olmucci, Poddubnyy Oleksandr. "Investigating Single Translation Function CycleGANs." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16126/.

Full text
Abstract:
With the advent of Deep Learning, we have been able to find solutions to many problems which didn't have an algorithmic solution, among these the image-to-image translation problem. One approach to solve it is by using the CycleGAN framework, which allows to learn mappings between two given image categories (or classes) that aren't necessarily paired. In this dissertation we present some attempts that were done in order to use the CycleGAN approach to perform image translations between more than two image classes at a time.
APA, Harvard, Vancouver, ISO, and other styles
6

Chatterjee, Rajen. "Automatic Post-Editing for Machine Translation." Doctoral thesis, Università degli studi di Trento, 2019. http://hdl.handle.net/11572/242495.

Full text
Abstract:
Automatic Post-Editing (APE) aims to correct systematic errors in a machine translated text. This is primarily useful when the machine translation (MT) system is not accessible for improvement, leaving APE as a viable option to improve translation quality as a downstream task - which is the focus of this thesis. This field has received less attention compared to MT due to several reasons, which include: the limited availability of data to perform a sound research, contrasting views reported by different researchers about the effectiveness of APE, and limited attention from the industry to use APE in current production pipelines. In this thesis, we perform a thorough investigation of APE as a down- stream task in order to: i) understand its potential to improve translation quality; ii) advance the core technology - starting from classical methods to recent deep-learning based solutions; iii) cope with limited and sparse data; iv) better leverage multiple input sources; v) mitigate the task-specific problem of over-correction; vi) enhance neural decoding to leverage external knowledge; and vii) establish an online learning framework to handle data diversity in real-time. All the above contributions are discussed across several chapters, and most of them are evaluated in the APE shared task organized each year at the Conference on Machine Translation. Our efforts in improving the technology resulted in the best system at the 2017 APE shared task, and our work on online learning received a distinguished paper award at the Italian Conference on Computational Linguistics. Overall, outcomes and findings of our work have boost interest among researchers and attracted industries to examine this technology to solve real-word problems.
APA, Harvard, Vancouver, ISO, and other styles
7

Caglayan, Ozan. "Multimodal Machine Translation." Thesis, Le Mans, 2019. http://www.theses.fr/2019LEMA1016/document.

Full text
Abstract:
La traduction automatique vise à traduire des documents d’une langue à une autre sans l’intervention humaine. Avec l’apparition des réseaux de neurones profonds (DNN), la traduction automatique neuronale(NMT) a commencé à dominer le domaine, atteignant l’état de l’art pour de nombreuses langues. NMT a également ravivé l’intérêt pour la traduction basée sur l’interlangue grâce à la manière dont elle place la tâche dans un cadre encodeur-décodeur en passant par des représentations latentes. Combiné avec la flexibilité architecturale des DNN, ce cadre a aussi ouvert une piste de recherche sur la multimodalité, ayant pour but d’enrichir les représentations latentes avec d’autres modalités telles que la vision ou la parole, par exemple. Cette thèse se concentre sur la traduction automatique multimodale(MMT) en intégrant la vision comme une modalité secondaire afin d’obtenir une meilleure compréhension du langage, ancrée de façon visuelle. J’ai travaillé spécifiquement avec un ensemble de données contenant des images et leurs descriptions traduites, où le contexte visuel peut être utile pour désambiguïser le sens des mots polysémiques, imputer des mots manquants ou déterminer le genre lors de la traduction vers une langue ayant du genre grammatical comme avec l’anglais vers le français. Je propose deux approches principales pour intégrer la modalité visuelle : (i) un mécanisme d’attention multimodal qui apprend à prendre en compte les représentations latentes des phrases sources ainsi que les caractéristiques visuelles convolutives, (ii) une méthode qui utilise des caractéristiques visuelles globales pour amorcer les encodeurs et les décodeurs récurrents. Grâce à une évaluation automatique et humaine réalisée sur plusieurs paires de langues, les approches proposées se sont montrées bénéfiques. Enfin,je montre qu’en supprimant certaines informations linguistiques à travers la dégradation systématique des phrases sources, la véritable force des deux méthodes émerge en imputant avec succès les noms et les couleurs manquants. Elles peuvent même traduire lorsque des morceaux de phrases sources sont entièrement supprimés
Machine translation aims at automatically translating documents from one language to another without human intervention. With the advent of deep neural networks (DNN), neural approaches to machine translation started to dominate the field, reaching state-ofthe-art performance in many languages. Neural machine translation (NMT) also revived the interest in interlingual machine translation due to how it naturally fits the task into an encoder-decoder framework which produces a translation by decoding a latent source representation. Combined with the architectural flexibility of DNNs, this framework paved the way for further research in multimodality with the objective of augmenting the latent representations with other modalities such as vision or speech, for example. This thesis focuses on a multimodal machine translation (MMT) framework that integrates a secondary visual modality to achieve better and visually grounded language understanding. I specifically worked with a dataset containing images and their translated descriptions, where visual context can be useful forword sense disambiguation, missing word imputation, or gender marking when translating from a language with gender-neutral nouns to one with grammatical gender system as is the case with English to French. I propose two main approaches to integrate the visual modality: (i) a multimodal attention mechanism that learns to take into account both sentence and convolutional visual representations, (ii) a method that uses global visual feature vectors to prime the sentence encoders and the decoders. Through automatic and human evaluation conducted on multiple language pairs, the proposed approaches were demonstrated to be beneficial. Finally, I further show that by systematically removing certain linguistic information from the input sentences, the true strength of both methods emerges as they successfully impute missing nouns, colors and can even translate when parts of the source sentences are completely removed
APA, Harvard, Vancouver, ISO, and other styles
8

Sandström, Emil. "Molecular Optimization Using Graph-to-Graph Translation." Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-172584.

Full text
Abstract:
Drug development is a protracted and expensive process. One of the main challenges indrug discovery is to find molecules with desirable properties. Molecular optimization is thetask of optimizing precursor molecules by affording them with desirable properties. Recentadvancement in Artificial Intelligence, has led to deep learning models designed for molecularoptimization. These models, that generates new molecules with desirable properties, have thepotential to accelerate the drug discovery. In this thesis, I evaluate the current state-of-the-art graph-to-graph translation model formolecular optimization, the HierG2G. I examine the HierG2G’s performance using three testcases, where the second test is designed, with the help of chemical experts, to represent a commonmolecular optimization task. The third test case, tests the HierG2G’s performance on,for the model, previously unseen molecules. I conclude that, in each of the test cases, the HierG2Gcan successfully generate structurally similar molecules with desirable properties givena source molecule and an user-specified desired property change. Further, I benchmark the HierG2Gagainst two famous string-based models, the seq2seq and the Transformer. My resultsuggests that the seq2seq is the overall best model for molecular optimization, but due to thevarying performance among the models, I encourage a potential user to simultaneously use allthree models for molecular optimization.
APA, Harvard, Vancouver, ISO, and other styles
9

García, Martínez Mercedes. "Factored neural machine translation." Thesis, Le Mans, 2018. http://www.theses.fr/2018LEMA1002/document.

Full text
Abstract:
La diversité des langues complexifie la tâche de communication entre les humains à travers les différentes cultures. La traduction automatique est un moyen rapide et peu coûteux pour simplifier la communication interculturelle. Récemment, laTraduction Automatique Neuronale (NMT) a atteint des résultats impressionnants. Cette thèse s'intéresse à la Traduction Automatique Neuronale Factorisé (FNMT) qui repose sur l'idée d'utiliser la morphologie et la décomposition grammaticale des mots (lemmes et facteurs linguistiques) dans la langue cible. Cette architecture aborde deux défis bien connus auxquelles les systèmes NMT font face. Premièrement, la limitation de la taille du vocabulaire cible, conséquence de la fonction softmax, qui nécessite un calcul coûteux à la couche de sortie du réseau neuronale, conduisant à un taux élevé de mots inconnus. Deuxièmement, le manque de données adéquates lorsque nous sommes confrontés à un domaine spécifique ou une langue morphologiquement riche. Avec l'architecture FNMT, toutes les inflexions des mots sont prises en compte et un vocabulaire plus grand est modélisé tout en gardant un coût de calcul similaire. De plus, de nouveaux mots non rencontrés dans les données d'entraînement peuvent être générés. Dans ce travail, j'ai développé différentes architectures FNMT en utilisant diverses dépendances entre les lemmes et les facteurs. En outre, j'ai amélioré la représentation de la langue source avec des facteurs. Le modèle FNMT est évalué sur différentes langues dont les plus riches morphologiquement. Les modèles à l'état de l'art, dont certains utilisant le Byte Pair Encoding (BPE) sont comparés avec le modèle FNMT en utilisant des données d'entraînement de petite et de grande taille. Nous avons constaté que les modèles utilisant les facteurs sont plus robustes aux conditions d'entraînement avec des faibles ressources. Le FNMT a été combiné avec des unités BPE permettant une amélioration par rapport au modèle FNMT entrainer avec des données volumineuses. Nous avons expérimenté avec dfférents domaines et nous avons montré des améliorations en utilisant les modèles FNMT. De plus, la justesse de la morphologie est mesurée à l'aide d'un ensemble de tests spéciaux montrant l'avantage de modéliser explicitement la morphologie de la cible. Notre travail montre les bienfaits de l'applicationde facteurs linguistiques dans le NMT
Communication between humans across the lands is difficult due to the diversity of languages. Machine translation is a quick and cheap way to make translation accessible to everyone. Recently, Neural Machine Translation (NMT) has achievedimpressive results. This thesis is focus on the Factored Neural Machine Translation (FNMT) approach which is founded on the idea of using the morphological and grammatical decomposition of the words (lemmas and linguistic factors) in the target language. This architecture addresses two well-known challenges occurring in NMT. Firstly, the limitation on the target vocabulary size which is a consequence of the computationally expensive softmax function at the output layer of the network, leading to a high rate of unknown words. Secondly, data sparsity which is arising when we face a specific domain or a morphologically rich language. With FNMT, all the inflections of the words are supported and larger vocabulary is modelled with similar computational cost. Moreover, new words not included in the training dataset can be generated. In this work, I developed different FNMT architectures using various dependencies between lemmas and factors. In addition, I enhanced the source language side also with factors. The FNMT model is evaluated on various languages including morphologically rich ones. State of the art models, some using Byte Pair Encoding (BPE) are compared to the FNMT model using small and big training datasets. We found out that factored models are more robust in low resource conditions. FNMT has been combined with BPE units performing better than pure FNMT model when trained with big data. We experimented with different domains obtaining improvements with the FNMT models. Furthermore, the morphology of the translations is measured using a special test suite showing the importance of explicitly modeling the target morphology. Our work shows the benefits of applying linguistic factors in NMT
APA, Harvard, Vancouver, ISO, and other styles
10

Bujwid, Sebastian. "GANtruth – a regularization method for unsupervised image-to-image translation." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233849.

Full text
Abstract:
In this work, we propose a novel and effective method for constraining the output space of the ill-posed problem of unsupervised image-to-image translation. We make the assumption that the environment of the source domain is known, and we propose to explicitly enforce preservation of the ground-truth labels on the images translated from the source to the target domain. We run empirical experiments on preserving information such as semantic segmentation and disparity and show evidence that our method achieves improved performance over the baseline model UNIT on translating images from SYNTHIA to Cityscapes. The generated images are perceived as more realistic in human surveys and have reduced errors when using them as adapted images in the domain adaptation scenario. Moreover, the underlying ground-truth preservation assumption is complementary to alternative approaches and by combining it with the UNIT framework, we improve the results even further.
I det här arbetet föreslår vi en ny och effektiv metod för att begränsa värdemängden för det illa-definierade problemet som utgörs av oövervakad bild-till-bild-översättning. Vi antar att miljön i källdomänen är känd, och vi föreslår att uttryckligen framtvinga bevarandet av grundfaktaetiketterna på bilder översatta från källa till måldomän. Vi utför empiriska experiment där information som semantisk segmentering och skillnad bevaras och visar belägg för att vår metod uppnår förbättrad prestanda över baslinjemetoden UNIT på att översätta bilder från SYNTHIA till Cityscapes. De genererade bilderna uppfattas som mer realistiska i undersökningar där människor tillfrågats och har minskat fel när de används som anpassade bilder i domänpassningsscenario. Dessutom är det underliggande grundfaktabevarande antagandet kompletterat med alternativa tillvägagångssätt och genom att kombinera det med UNIT-ramverket förbättrar vi resultaten ytterligare.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Books on the topic "DeepL Translator"

1

Bunt, Harry C. Trends in Parsing Technology: Dependency Parsing, Domain Adaptation, and Deep Parsing. Dordrecht: Springer Science+Business Media B.V., 2011.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
2

Marieluise, Fleisser. Marieluise Fleisser's 'The deep sea fish': A translation and critical examination. Ann Arbor: University Microfilms, 1997.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
3

Deep things out of darkness: The book of Job : essays and a new English translation. Kampen, Netherlands: Pharos, 1995.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
4

Haroutyunian, Sona, and Dario Miccoli. Orienti migranti: tra letteratura e traduzione. Venice: Fondazione Università Ca’ Foscari, 2020. http://dx.doi.org/10.30687/978-88-6969-499-8.

Full text
Abstract:
The book series, edited by Nicoletta Pesaro and sponsored by the Department of Asian and North African Studies, aims to give voice to a time-honoured branch of theoretical and practical research across the disciplines and research domains within the Department. The series aims to establish a platform for scholarly discussion and a space for international dialogue on the translation of Asian and North African languages. In doing so, the project aims to observe and verify the translingual and transcultural dynamics triggered by translation from and into said ‘languages-cultures’, as well as to identify and explore the deep cultural mechanisms and structures involved in interethnic behaviours and relationships. Translation is also a major research tool in the humanities. As a matter of fact, a hermeneutic potential in terms of cultural mediation is inherent in translation activities and in the reflection on translation: it is precisely this potential that allows scholars, in both their research and dissemination work, to bring to the surface the interethnic and intercultural dynamics regulating the relationships between civilisations, both diachronically and synchronically. The project is a continuation and a development of the research carried out in recent years by the former Department of East Asian Studies – now Department of Asian and North African Studies – of Ca’ Foscari University of Venice through a series of initiatives organised by the research group on the translation of Asian languages “Laboratorio sulla Traduzione delle Lingue orientali” (Laboratori sulle lingue orientali). Such activities involved periodical meetings on translation, whose objective was to introduce and discuss specific issues in translation from and into Asian languages, as well as several international events (workshops, conferences, and symposia).
APA, Harvard, Vancouver, ISO, and other styles
5

Favaro, Alice. Después de la caída del ‘ángel’. Venice: Edizioni Ca' Foscari, 2020. http://dx.doi.org/10.30687/978-88-6969-416-5.

Full text
Abstract:
Ángel Bonomini was born in Buenos Aires in 1929 where he lived until his death at the age of sixty-four in 1994. He worked for various newspapers and magazines as an art critic and translator, but always maintaining his literary activity. He inherited the tradition of the Argentine fantastic and was a prolific writer: his production includes essays, poems and fantastic tales.Although he lived in a period of great cultural splendor and his literary talent was recognised by authors such as Borges and Bioy Casares, he fell into an unexplained oblivion, disappearing quite early from the contemporary intellectual environment. His first poems, which date back to the 1950s, were published in Sur magazine and some of his tales were included in well-known anthologies of fantastic literature.Among his collections of poems there are: Primera enunciación (1947), Argumento del enamorado. Baladas con Ángel (1952) written with María Elena Walsh, Torres para el silencio (1982) and Poética (1994). In 1972 he achieved great success with the publication of his first collection of fantastic tales, Los novicios de Lerna, followed by the publication of other books: Libro de los casos (1975), Los lentos elefantes de Milán (1978), Cuentos de amor (1982), Historias secretas (1985) and Más allá del puente (1996), posthumously published.A particular use of the fantastic characterises his work and distinguishes him from his contemporary authors. In his tales there is a continuous contrast between metaphysics and existentialism; in this way, he makes a deep investigation of the reality and, at the same time, he tries to go beyond it.This volume aims to analyse some emblematic tales by Bonomini in which it is possible to find the main topoi of Argentine fantastic and to understand why the author’s literary work is worth studying.
APA, Harvard, Vancouver, ISO, and other styles
6

Tyndale. Drink Deeply Bible: New Living Translation, Red Plastic Case (Bible Nlt). Tyndale House Publishers, 2007.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
7

Smith, Valerie Rae. Marieluise Fleisser's The deep sea fish: A translation and critical examination. 1996.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
8

Tyndale. Drink Deeply Bible: New Living Translation, Blue Goldfish Plastic Case (Bible Nlt). Tyndale House Publishers, 2007.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
9

Tyndale. Drink Deeply Bible: New Living Translation, Orange Waves Plastic Case (Bible Nlt). Tyndale House Publishers, 2007.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
10

Shanmugamani, Rajalingappaa, Luca Massaron, Alberto Boschetti, Alexey Grigorev, and Abhishek Thakur. TensorFlow Deep Learning Projects: 10 real-world projects on computer vision, machine translation, chatbots, and reinforcement learning. Packt Publishing, 2018.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "DeepL Translator"

1

Steiner, Riccardo. "“The Deep Open Sea”1 “l’alto mare aperto”." In Translation / Transformation, 88–119. Abingdon, Oxon; New York, NY: Routledge, 2021. | Series: New library of psychoanalysis: Routledge, 2021. http://dx.doi.org/10.4324/9781003096399-5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Liu, Yang, and Jiajun Zhang. "Deep Learning in Machine Translation." In Deep Learning in Natural Language Processing, 147–83. Singapore: Springer Singapore, 2018. http://dx.doi.org/10.1007/978-981-10-5209-5_6.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Katzir, Oren, Dani Lischinski, and Daniel Cohen-Or. "Cross-Domain Cascaded Deep Translation." In Computer Vision – ECCV 2020, 673–89. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-58536-5_40.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Skansi, Sandro, Leo Mršić, and Ines Skelac. "A Lost Croatian Cybernetic Machine Translation Program." In Guide to Deep Learning Basics, 67–78. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-37591-1_7.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Scott, Bernard. "Deep Learning MT and Logos Model." In Translation, Brains and the Computer, 173–202. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-76629-4_8.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Swathi, S., and L. S. Jayashree. "Machine Translation Using Deep Learning: A Comparison." In Proceedings of International Conference on Artificial Intelligence, Smart Grid and Smart City Applications, 389–95. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-24051-6_38.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Minh, Tuan Nguyen, Phayung Meesad, and Huy Cuong Nguyen Ha. "English-Vietnamese Machine Translation Using Deep Learning." In Lecture Notes in Networks and Systems, 99–107. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-79757-7_10.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Murez, Zak, Soheil Kolouri, David Kriegman, Ravi Ramamoorthi, and Kyungnam Kim. "Domain Adaptation via Image to Image Translation." In Domain Adaptation in Computer Vision with Deep Learning, 117–36. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-45529-3_7.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Zhang, Lin, Tiziano Portenier, Christoph Paulus, and Orcun Goksel. "Deep Image Translation for Enhancing Simulated Ultrasound Images." In Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis, 85–94. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-60334-2_9.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Guard, Nahid, and Suneeta V. Budihal. "Image-To-Image Translation Using Deep Convolutional GANs." In Information and Communication Technology for Competitive Strategies (ICTCS 2020), 569–77. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-16-0739-4_54.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "DeepL Translator"

1

Noever, David, Josh Kalin, Matthew Ciolino, Dom Hambrick, and Gerry Dozier. "Local Translation Services for Neglected Languages." In 8th International Conference on Artificial Intelligence and Applications (AIAP 2021). AIRCC Publishing Corporation, 2021. http://dx.doi.org/10.5121/csit.2021.110110.

Full text
Abstract:
Taking advantage of computationally lightweight, but high-quality translators prompt consideration of new applications that address neglected languages. For projects with protected or personal data, translators for less popular or low-resource languages require specific compliance checks before posting to a public translation API. In these cases, locally run translators can render reasonable, cost-effective solutions if done with an army of offline, smallscale pair translators. Like handling a specialist’s dialect, this research illustrates translating two historically interesting, but obfuscated languages: 1) hacker-speak (“l33t”) and 2) reverse (or “mirror”) writing as practiced by Leonardo da Vinci. The work generalizes a deep learning architecture to translatable variants of hacker-speak with lite, medium, and hard vocabularies. The original contribution highlights a fluent translator of hacker-speak in under 50 megabytes and demonstrates a companion text generator for augmenting future datasets with greater than a million bilingual sentence pairs. A primary motivation stems from the need to understand and archive the evolution of the international computer community, one that continuously enhances their talent for speaking openly but in hidden contexts. This training of bilingual sentences supports deep learning models using a long short-term memory, recurrent neural network (LSTM-RNN). It extends previous work demonstrating an English-to-foreign translation service built from as little as 10,000 bilingual sentence pairs. This work further solves the equivalent translation problem in twenty-six additional (non-obfuscated) languages and rank orders those models and their proficiency quantitatively with Italian as the most successful and Mandarin Chinese as the most challenging. For neglected languages, the method prototypes novel services for smaller niche translations such as Kabyle (Algerian dialect) which covers between 5-7 million speakers but one which for most enterprise translators, has not yet reached development. One anticipates the extension of this approach to other important dialects, such as translating technical (medical or legal) jargon and processing health records or handling many of the dialects collected from specialized domains (mixed languages like “Spanglish”, acronym-laden Twitter feeds, or urban slang).
APA, Harvard, Vancouver, ISO, and other styles
2

Cai, Ruichu, Boyan Xu, Zhenjie Zhang, Xiaoyan Yang, Zijian Li, and Zhihao Liang. "An Encoder-Decoder Framework Translating Natural Language to Database Queries." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/553.

Full text
Abstract:
Machine translation is going through a radical revolution, driven by the explosive development of deep learning techniques using Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In this paper, we consider a special case in machine translation problems, targeting to convert natural language into Structured Query Language (SQL) for data retrieval over relational database. Although generic CNN and RNN learn the grammar structure of SQL when trained with sufficient samples, the accuracy and training efficiency of the model could be dramatically improved, when the translation model is deeply integrated with the grammar rules of SQL. We present a new encoder-decoder framework, with a suite of new approaches, including new semantic features fed into the encoder, grammar-aware states injected into the memory of decoder, as well as recursive state management for sub-queries. These techniques help the neural network better focus on understanding semantics of operations in natural language and save the efforts on SQL grammar learning. The empirical evaluation on real world database and queries show that our approach outperform state-of-the-art solution by a significant margin.
APA, Harvard, Vancouver, ISO, and other styles
3

Yedidiah, S. "Translating Equations Into Their Physical Meaning as an Effective Tool of Engineering." In ASME 2006 2nd Joint U.S.-European Fluids Engineering Summer Meeting Collocated With the 14th International Conference on Nuclear Engineering. ASMEDC, 2006. http://dx.doi.org/10.1115/fedsm2006-98012.

Full text
Abstract:
This paper is an extension of the discussion pertaining the need for, and the benefits of the capability to translate a mathematical expression into a description of a relevant physical event, respectively of a physical situation. It shows, how such a translation has made it possible to recognize the shortcomings of the deeply-rooted conception, that the outlet angle of the impeller blades is the most significant design parameter of a rotodynamic pump. The awareness of these shortcomings, in turn, has led already to the development of a more reliable approach for calculating the heads generated by a rotodynamic impeller, (Compare Fig. 2.). It has also made possible to solve to a number of additional problems which, in the past, could be solved only by the costly and time consuming method of trial and error. This paper also discusses the physical meaning of the Navier-Stokes equations. It shows how the translation of these equations into their physical meaning made it possible to explain several seemingly enigmatic results of tests. In addition to the above, this paper also discusses a number of problems which need yet to be explored in the future, in order to be able to turn CFD into a useful tool for the design of rotodynamic pumps.
APA, Harvard, Vancouver, ISO, and other styles
4

Kobus, Catherine, Josep Crego, and Jean Senellart. "Domain Control for Neural Machine Translation." In RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning. Incoma Ltd. Shoumen, Bulgaria, 2017. http://dx.doi.org/10.26615/978-954-452-049-6_049.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Miceli Barone, Antonio Valerio, Jindřich Helcl, Rico Sennrich, Barry Haddow, and Alexandra Birch. "Deep architectures for Neural Machine Translation." In Proceedings of the Second Conference on Machine Translation. Stroudsburg, PA, USA: Association for Computational Linguistics, 2017. http://dx.doi.org/10.18653/v1/w17-4710.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Nakov, Preslav, and Stephan Vogel. "Robust Tuning Datasets for Statistical Machine Translation." In RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning. Incoma Ltd. Shoumen, Bulgaria, 2017. http://dx.doi.org/10.26615/978-954-452-049-6_071.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

"Session details: Deep-1 (Image Translation)." In 2018 ACM Multimedia Conference, chair Nicu Sebe. New York, New York, USA: ACM Press, 2018. http://dx.doi.org/10.1145/3240508.3286919.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Sebe, Nicu. "Session details: Deep-1 (Image Translation)." In MM '18: ACM Multimedia Conference. New York, NY, USA: ACM, 2018. http://dx.doi.org/10.1145/3286919.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Hong, Zhang-Wei, Yu-Ming Chen, Hsuan-Kung Yang, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Brian Hsi-Lin Ho, et al. "Virtual-to-Real: Learning to Control in Visual Semantic Segmentation." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/682.

Full text
Abstract:
Collecting training data from the physical world is usually time-consuming and even dangerous for fragile robots, and thus, recent advances in robot learning advocate the use of simulators as the training platform. Unfortunately, the reality gap between synthetic and real visual data prohibits direct migration of the models trained in virtual worlds to the real world. This paper proposes a modular architecture for tackling the virtual-to-real problem. The proposed architecture separates the learning model into a perception module and a control policy module, and uses semantic image segmentation as the meta representation for relating these two modules. The perception module translates the perceived RGB image to semantic image segmentation. The control policy module is implemented as a deep reinforcement learning agent, which performs actions based on the translated image segmentation. Our architecture is evaluated in an obstacle avoidance task and a target following task. Experimental results show that our architecture significantly outperforms all of the baseline methods in both virtual and real environments, and demonstrates a faster learning curve than them. We also present a detailed analysis for a variety of variant configurations, and validate the transferability of our modular architecture.
APA, Harvard, Vancouver, ISO, and other styles
10

Kocmi, Tom, and Ondřej Bojar. "Curriculum Learning and Minibatch Bucketing in Neural Machine Translation." In RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning. Incoma Ltd. Shoumen, Bulgaria, 2017. http://dx.doi.org/10.26615/978-954-452-049-6_050.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "DeepL Translator"

1

Terzyan, Aram. Post-Soviet State - Building in Kyrgyzstan: Behind and Beyond the Revolutions. Eurasia Institutes, April 2021. http://dx.doi.org/10.47669/caps-1-2021.

Full text
Abstract:
This paper explores post-Soviet state-building in Kyrgyzstan, with a focus on the root causes of the three revolutions faced by the country. It suggests that the revolutions have not produced significant results in terms of fundamental economic and political reforms. Rather, Kyrgyzstan has turned into the Central Asian “island of instability”. The situation is compounded by deep- rooted inter-ethnic tensions, the prevalence of traditional informal institutions and weakness of democratic institutions, as well as country’s heavy reliance on international donors. The presidential elections and constitutional referendum of 2021 have provided grounds for cautious optimism. A question remains of whether and to what extent Sadyr Japarov’s ambitious agenda will translate into reality, thus leading the country to prosperity and stability.
APA, Harvard, Vancouver, ISO, and other styles
2

Beuermann, Diether, Henry Mooney, Elton Bollers, David Rosenblatt, Maria Alejandra Zegarra, Laura Giles Álvarez, Gralyn Frazier, et al. Caribbean Quarterly Bulletin 2020: Volume 9: Issue 4, December 2020. Inter-American Development Bank, December 2020. http://dx.doi.org/10.18235/0002948.

Full text
Abstract:
For most Caribbean countries, the COVID-19 pandemic will translate into the deepest single-year contraction of real GDP on record in 2020. With the exception of Guyana, countries have experienced deep recessions, severe increases in unemployment, and long-lasting damage to many corporate and household balance sheets. The social consequences of the crisis continue to mount, and despite governments best efforts to buffer the shock to families, enterprises, and domestic markets, there remains a dire need for continued and more broad-based stimulus to ensure that economic capital both human and other wise remains intact. This edition of the Caribbean Quarterly Bulletin briefly reflects on notable economic developments in 2020, then shifts to longer-term issues, including a summary of an upcoming IDB publication, Economic Institutions for a Resilient Caribbean, as well as summaries of the book's key diagnostics and recommendations for each country. In some cases, country sections focus on specific areas of institutional reforms. For example, the Suriname section focuses on fiscal institutions, given the public debt distress there.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'DeepL Translator' for particular source types:
Journal articles Dissertations / Theses Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography