New MLLP article on language technologies for MOOCs and OER published in the Journal of Educational Technology and Society

MLLPThe article Multilingual videos for MOOCs and OER“, by Juan Daniel Valor Miró and other MLLP members, has been published in the March 2018 issue of the Journal of Educational Technology and Society.

The article’s authors, MLLP members Juan Daniel Valor Miró, Pau Baquero-Arnal, Jorge Civera and Alfons Juan, together with Universitat Politècnica de València’s Carlos Turró, have summarized it in the following abstract:

Massive Open Online Courses (MOOCs) and Open Educational Resources (OER) are rapidly growing, but are not usually offered in multiple languages due to the lack of cost-effective solutions to translate the different objects comprising them and particularly videos. However, current state-of-the-art automatic speech recognition (ASR) and machine translation (MT) techniques have reached a level of maturity which opens the possibility of producing multilingual video subtitles of publishable quality at low cost. This work summarizes authors’ experience in exploring this possibility in two real-life case studies: a MOOC platform and a large video lecture repository. Apart from describing the systems, tools and integration components employed for such purpose, a comprehensive evaluation of the results achieved is provided in terms of quality and efficiency. More precisely, it is shown that draft multilingual subtitles produced by domain-adapted ASR/MT systems reach a level of accuracy that make them worth post-editing, instead of generating them ex novo, saving approximately 25%–75% of the time. Finally, the results reported on user multilingual data consumption reflect that multilingual subtitles have had a very positive impact in our case studies boosting student enrolment, in the case of the MOOC platform, by 70% relative.

The Journal of Educational Technology and Society, published by the National Taiwan Normal University, is an open access academic journal which seeks academic articles on the issues affecting the developers of educational systems and educators who implement and manage such systems, discussing the perspectives of both communities and their relation to each other. With a JCR 2016 impact factor of 1.584 (5-year: 2.034), it’s a Q2 journal in the category of Education and Educational Research.

This new article follows and expands on a line of journal and conference publications by Juan Daniel Valor Miró on the evaluation of the post-edition of automatic transcriptions and translations of video lectures, including a 2014 article in Routledge’s Open Learning: The Journal of Open, Distance and e-Learning titled “Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures“, and a paper for EC-TEL 2015 titled “Efficient Generation of High-Quality Multilingual Subtitles for Video Lecture Repositories“. All of these results are part of Juan Daniel’s PhD thesis, “Evaluation of innovative computer-assisted transcription and translation strategies for video lecture repositories”, which he successfully defended at UPV on 22 September 2017.

In the last six years (2012-2018), MLLP members have published 15 international journal articles (IEEE-ACM Trans. Audio Speech Lang., 2018; Pattern Recognition Letters, 51, 2015; Pattern Recognition, 45 (9), 2012; …) and over 30 international conference papers (Interspeech 2016AMTA 2014; ICASSP 2013;  EACL 2012; …). You can browse through all of the group’s 200+ publications (since 1991) in the Publications section in our website.

Posted in All, Publications and tagged , , , .