Post-editing through Speech Recognition: A Feasibility Study with Post-editor Trainees

Bartolomé Mesa-Lao

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

    Abstract

    In the past couple of years automatic speech recognition (ASR) software has quietly created a niche for itself in many situations of our lives. Nowadays it can be found at the other end of customer-support hotlines, it is built into operating systems and it is offered as an alternative text-input method for smartphones. On another front, given the significant improvements in Machine Translation (MT) quality and the increasing
    demand for translations, post-editing of MT is becoming a popular practice in the translation industry, since it has been shown to allow for larger volumes of translations to be produced saving time and costs. The translation industry is at a deeply transformative point in its evolution and the coming years herald an era of converge where speech technology could make a difference. As post-editing services are becoming a common practice among language service providers and speech recognition is gaining momentum, it seems reasonable to explore the interplay between
    both fields in a feasibility study.
    In the context of machine-aided human translation (MAHT), different scenarios have been investigated where human translators interact with a computer through a variety of input modalities (i.e. typing, handwriting and speaking) to improve the efficiency and accuracy of the translation process. However, further studies need to be conducted to build up new knowledge about the way in which state-of-the-art speech recognition
    software can be applied to the post-editing process. As a continuation of the pioneering work done in the SEECAT project, our presentation will report on a feasibility study where post-editor trainees will be asked to post-edit raw MT using voice and keyboard as an input method. This feasibility study will explore the potential of combining one of the most popular computer-aided translation workbenches in the market (i.e. MemoQ) together with one of the most well-known ASR packages (i.e. Dragon Naturally Speaking from Nuance). Two data correction modes will be considered: a) keyboard vs. b) keyboard and speech combined. These two different ways of verifying and correcting raw MT output will be examined making comparisons in terms of: i) overall time to complete the task, ii) final quality of the target text, and iii) user satisfaction.
    Original languageEnglish
    Publication date2014
    Number of pages1
    Publication statusPublished - 2014
    Event2014 CRITT - WCRE Conference: Translation in Transition: Between Cognition, Computing and Technology - Copenhagen Business School, Frederiksberg, Denmark
    Duration: 30 Jan 201431 Jan 2014
    http://bridge.cbs.dk/platform/?q=conference2014

    Conference

    Conference2014 CRITT - WCRE Conference
    LocationCopenhagen Business School
    CountryDenmark
    CityFrederiksberg
    Period30/01/201431/01/2014
    Internet address

    Cite this

    Mesa-Lao, B. (2014). Post-editing through Speech Recognition: A Feasibility Study with Post-editor Trainees. Abstract from 2014 CRITT - WCRE Conference, Frederiksberg, Denmark.
    Mesa-Lao, Bartolomé . / Post-editing through Speech Recognition : A Feasibility Study with Post-editor Trainees. Abstract from 2014 CRITT - WCRE Conference, Frederiksberg, Denmark.1 p.
    @conference{4662d3767cff4301b97bc05069cf3235,
    title = "Post-editing through Speech Recognition: A Feasibility Study with Post-editor Trainees",
    abstract = "In the past couple of years automatic speech recognition (ASR) software has quietly created a niche for itself in many situations of our lives. Nowadays it can be found at the other end of customer-support hotlines, it is built into operating systems and it is offered as an alternative text-input method for smartphones. On another front, given the significant improvements in Machine Translation (MT) quality and the increasingdemand for translations, post-editing of MT is becoming a popular practice in the translation industry, since it has been shown to allow for larger volumes of translations to be produced saving time and costs. The translation industry is at a deeply transformative point in its evolution and the coming years herald an era of converge where speech technology could make a difference. As post-editing services are becoming a common practice among language service providers and speech recognition is gaining momentum, it seems reasonable to explore the interplay betweenboth fields in a feasibility study. In the context of machine-aided human translation (MAHT), different scenarios have been investigated where human translators interact with a computer through a variety of input modalities (i.e. typing, handwriting and speaking) to improve the efficiency and accuracy of the translation process. However, further studies need to be conducted to build up new knowledge about the way in which state-of-the-art speech recognitionsoftware can be applied to the post-editing process. As a continuation of the pioneering work done in the SEECAT project, our presentation will report on a feasibility study where post-editor trainees will be asked to post-edit raw MT using voice and keyboard as an input method. This feasibility study will explore the potential of combining one of the most popular computer-aided translation workbenches in the market (i.e. MemoQ) together with one of the most well-known ASR packages (i.e. Dragon Naturally Speaking from Nuance). Two data correction modes will be considered: a) keyboard vs. b) keyboard and speech combined. These two different ways of verifying and correcting raw MT output will be examined making comparisons in terms of: i) overall time to complete the task, ii) final quality of the target text, and iii) user satisfaction.",
    author = "Bartolom{\'e} Mesa-Lao",
    year = "2014",
    language = "English",
    note = "null ; Conference date: 30-01-2014 Through 31-01-2014",
    url = "http://bridge.cbs.dk/platform/?q=conference2014",

    }

    Mesa-Lao, B 2014, 'Post-editing through Speech Recognition: A Feasibility Study with Post-editor Trainees', Frederiksberg, Denmark, 30/01/2014 - 31/01/2014, .

    Post-editing through Speech Recognition : A Feasibility Study with Post-editor Trainees. / Mesa-Lao, Bartolomé .

    2014. Abstract from 2014 CRITT - WCRE Conference, Frederiksberg, Denmark.

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

    TY - ABST

    T1 - Post-editing through Speech Recognition

    T2 - A Feasibility Study with Post-editor Trainees

    AU - Mesa-Lao, Bartolomé

    PY - 2014

    Y1 - 2014

    N2 - In the past couple of years automatic speech recognition (ASR) software has quietly created a niche for itself in many situations of our lives. Nowadays it can be found at the other end of customer-support hotlines, it is built into operating systems and it is offered as an alternative text-input method for smartphones. On another front, given the significant improvements in Machine Translation (MT) quality and the increasingdemand for translations, post-editing of MT is becoming a popular practice in the translation industry, since it has been shown to allow for larger volumes of translations to be produced saving time and costs. The translation industry is at a deeply transformative point in its evolution and the coming years herald an era of converge where speech technology could make a difference. As post-editing services are becoming a common practice among language service providers and speech recognition is gaining momentum, it seems reasonable to explore the interplay betweenboth fields in a feasibility study. In the context of machine-aided human translation (MAHT), different scenarios have been investigated where human translators interact with a computer through a variety of input modalities (i.e. typing, handwriting and speaking) to improve the efficiency and accuracy of the translation process. However, further studies need to be conducted to build up new knowledge about the way in which state-of-the-art speech recognitionsoftware can be applied to the post-editing process. As a continuation of the pioneering work done in the SEECAT project, our presentation will report on a feasibility study where post-editor trainees will be asked to post-edit raw MT using voice and keyboard as an input method. This feasibility study will explore the potential of combining one of the most popular computer-aided translation workbenches in the market (i.e. MemoQ) together with one of the most well-known ASR packages (i.e. Dragon Naturally Speaking from Nuance). Two data correction modes will be considered: a) keyboard vs. b) keyboard and speech combined. These two different ways of verifying and correcting raw MT output will be examined making comparisons in terms of: i) overall time to complete the task, ii) final quality of the target text, and iii) user satisfaction.

    AB - In the past couple of years automatic speech recognition (ASR) software has quietly created a niche for itself in many situations of our lives. Nowadays it can be found at the other end of customer-support hotlines, it is built into operating systems and it is offered as an alternative text-input method for smartphones. On another front, given the significant improvements in Machine Translation (MT) quality and the increasingdemand for translations, post-editing of MT is becoming a popular practice in the translation industry, since it has been shown to allow for larger volumes of translations to be produced saving time and costs. The translation industry is at a deeply transformative point in its evolution and the coming years herald an era of converge where speech technology could make a difference. As post-editing services are becoming a common practice among language service providers and speech recognition is gaining momentum, it seems reasonable to explore the interplay betweenboth fields in a feasibility study. In the context of machine-aided human translation (MAHT), different scenarios have been investigated where human translators interact with a computer through a variety of input modalities (i.e. typing, handwriting and speaking) to improve the efficiency and accuracy of the translation process. However, further studies need to be conducted to build up new knowledge about the way in which state-of-the-art speech recognitionsoftware can be applied to the post-editing process. As a continuation of the pioneering work done in the SEECAT project, our presentation will report on a feasibility study where post-editor trainees will be asked to post-edit raw MT using voice and keyboard as an input method. This feasibility study will explore the potential of combining one of the most popular computer-aided translation workbenches in the market (i.e. MemoQ) together with one of the most well-known ASR packages (i.e. Dragon Naturally Speaking from Nuance). Two data correction modes will be considered: a) keyboard vs. b) keyboard and speech combined. These two different ways of verifying and correcting raw MT output will be examined making comparisons in terms of: i) overall time to complete the task, ii) final quality of the target text, and iii) user satisfaction.

    M3 - Conference abstract for conference

    ER -

    Mesa-Lao B. Post-editing through Speech Recognition: A Feasibility Study with Post-editor Trainees. 2014. Abstract from 2014 CRITT - WCRE Conference, Frederiksberg, Denmark.