Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 165 for “"machine translation"”.

  1. Multimodal machine translation

    … there has been a lot of progress being made in machine translation through deep learning networks. But there is relatively lesser progress made in using images to catalyze the translation tasks. In this study, we explore various models to incorporate the image features in the machine translation

    uiuc Repository record for Multimodal machine translation (opens in a new tab)

  2. Robust Neural Machine Translation

    <p>This thesis aims for general robust Neural Machine Translation (NMT) that is agnostic to the test domain. NMT has achieved high quality on benchmarks with closed datasets such as WMT and NIST but can fail when the translation input contains noise due to, for example, mismatched domains or …

    cuny-grad Repository record for Robust Neural Machine Translation (opens in a new tab)

  3. Towards Gender-Inclusive Machine Translation

    Machine translation systems have become essential tools for cross-lingual communication, yet they systematically encode and perpetuate gender bias. When translating into grammatical gender languages such as Italian, Spanish, and German, these systems default to masculine forms for gender-ambiguous …

    trento Repository record for Towards Gender-Inclusive Machine Translation (opens in a new tab)

  4. Morphology, analogy and machine translation

    … two or more languages in a "transfer-based" MachineTranslation System. As to the nature and content of these representations, manyalternative proposals, put forward in both theoretical and computational linguistic circles,are carefully considered and extensively discussed. In particular, I …

    salford Repository record for Morphology, analogy and machine translation (opens in a new tab)

  5. Generate and repair machine translation.

    regina Repository record for Generate and repair machine translation. (opens in a new tab)

  6. Deep Syntax in Statistical Machine Translation

    Statistical Machine Translation (SMT) via deep syntactic transfer employs a three-stage architecture, (i) parse source language (SL) input, (ii) transfer SL deep syntactic structure to the target language (TL), and (iii) generate a TL translation. The deep syntactic transfer architecture achieves a …

    dcu Repository record for Deep Syntax in Statistical Machine Translation (opens in a new tab)

  7. Resourcing machine translation with parallel treebanks

    … of syntax-based approaches to data-driven machine translation (MT) are clear: given the right model, a combination of hierarchical structure, constituent labels and morphological information can be exploited to produce more fluent, grammatical translation output. This has been demonstrated …

    dcu Repository record for Resourcing machine translation with parallel treebanks (opens in a new tab)

  8. Lexical syntax for statistical machine translation

    Statistical Machine Translation (SMT) is by far the most dominant paradigm of Machine Translation. This can be justified by many reasons, such as accuracy, scalability, computational efficiency and fast adaptation to new languages and domains. However, current approaches of Phrase-based SMT lacks …

    dcu Repository record for Lexical syntax for statistical machine translation (opens in a new tab)

  9. Target-Dominant Chinese-English Machine Translation

    … describes a target-dominant Chinese-English machine translation system, which can translate a given Chinese news sentence into English. We conjecture that we can improve the state of the art of MT using a TDMT approach. This system has participated in the NIST (National Institute of Standards …

    byu Repository record for Target-Dominant Chinese-English Machine Translation (opens in a new tab)

  10. Domain adaptation for neural machine translation

    … of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, such translation models struggle when translating text of a specific domain. A domain may consist of text on a well-defined …

    cambridge Repository record for Domain adaptation for neural machine translation (opens in a new tab)

  11. Rich Features in Phrase-Based Machine Translation

    Název práce: Bohaté rysy ve frázovém strojovém překladu Autor: Kamil Kos Katedra (ústav): Ústav formální a aplikované lingvistiky Vedoucí diplomové práce: RNDr. Ondřej Bojar, Ph.D. e-mail vedoucího: bojar@ufal.mff.cuni.cz Klíčová slova: strojový překlad, hodnocení kvality, kontextový model, …

    charles-prague Repository record for Rich Features in Phrase-Based Machine Translation (opens in a new tab)

  12. Automatic Error Correction of Machine Translation Output

    Představujeme MLFix, systém pro automatickou statistickou post-editaci, který je duchovním následníkem pravidlového systému, Depfixu. Cílem této práce bylo prozkoumat možné postupy automatické identifikace nejčastějších morfologických chyb tvořených současnými systémy pro strojový překlad a …

    charles-prague Repository record for Automatic Error Correction of Machine Translation Output (opens in a new tab)

  13. Data-driven machine translation for sign languages

    … thesis explores the application of data-driven machine translation (MT) to sign languages (SLs). The provision of an SL MT system can facilitate communication between Deaf and hearing people by translating information into the native and preferred language of the individual. We begin with an …

    dcu Repository record for Data-driven machine translation for sign languages (opens in a new tab)

  14. Speech Adaptation Modeling for Statistical Machine Translation

    Spoken language translation (SLT) exists within one of the most challenging intersections of speech and natural language processing. While machine translation (MT) has demonstrated its effectiveness on the translation of textual data, the translation of spoken language remains a challenge, largely …

    trento Repository record for Speech Adaptation Modeling for Statistical Machine Translation (opens in a new tab)

  15. TransBooster:black box optimisation of machine translation systems

    Machine Translation (MT) systems tend to underperform when faced with long, linguistically complex sentences. Rule-based systems often trade a broad but shallow linguistic coverage for a deep, fine-grained analysis since hand-crafting rules based on detailed linguistic analyses is time-consuming, …

    dcu Repository record for TransBooster:black box optimisation of machine translation systems (opens in a new tab)

  16. Hybrid data-driven models of machine translation

    Corpus-based approaches to Machine Translation (MT) dominate the MT research field today, with Example-Based MT (EBMT) and Statistical MT (SMT) representing two different frameworks within the data-driven paradigm. EBMT has always made use of both phrasal and lexical correspondences to produce …

    dcu Repository record for Hybrid data-driven models of machine translation (opens in a new tab)

  17. Fine-grained error analysis in machine translation

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms

    uiuc Repository record for Fine-grained error analysis in machine translation (opens in a new tab)

  18. Exploiting monolingual data for neural machine translation

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms

    uiuc Repository record for Exploiting monolingual data for neural machine translation (opens in a new tab)

  19. Using linguistic knowledge in statistical machine translation

    … to enhance the performance of statistical machine translation (SMT). One of the advantages of the statistical approach to machine translation is that it is largely language-agnostic. Machine learning models are used to automatically learn translation patterns from data. SMT can, however, be …

    mit Repository record for Using linguistic knowledge in statistical machine translation (opens in a new tab)

Page 1 of 9