We compare machine learning approaches for sentence length reduction for automatic generation of subtitles for deaf and hearing-impaired people with a method which relies on hand-crafted deletion rules. We describe building the necessary resources for this task: a parallel corpus of examples of news broadcasts of the Flemish VRT broadcasting corporation, and a Dutch shallow parser based on the ...

Audiovisual Translation (AVT), and in particular subtitling, has been recognised as an area that could potentially benefit from the introduction of machine translation (followed by post-editing) [1],[2],[10],[15],[27],[28]. In recent years the demands on subtitlers have increased, while the payment to subtitlers and time allotted to produce the subtitles have both decreased. Therefore this mark...

This article describes a large-scale evaluation of the use of Statistical Machine Translation for professional subtitling. The work was carried out within the FP7 EU-funded project SUMAT and involved two rounds of evaluation: a quality evaluation and a measure of productivity gain/loss. We present the SMT systems built for the project and the corpora they were trained on, which combine professi...

Focusing on 48 Chinese films made by the representatives of fifth- and sixth-generation directors (i.e. Zhang Yimou, Chen Kaige, Jia Zhangke Feng Xiaogang), this paper reveals: (1) These directors’ preferences for themes with locality are related to popularity local literature except their nostalgia hometowns; (2) The overseas distribution these cannot be separated from support state policies, ...

This paper presents the virtual speech cuer built in the context of the ARTUS project aiming at watermarking hand and face gestures of a virtual animated agent in a broadcasted audiovisual sequence. For deaf televiewers that master cued speech, the animated agent can be then superimposed on demand and at the reception on the original broadcast as an alternative to subtitling. The paper presents...

This paper presents the virtual speech cuer built in the context of the ARTUS project aiming at watermarking hand and face gestures of a virtual animated agent in a broadcasted audiovisual sequence. For deaf televiewers that master cued speech, the animated agent can be then incrusted on demand and at the reception in the original broadcast as an alternative to subtitling. The paper presents th...

Focusing on contemporary Taiwanese popular culture, this paper delineates how the subtitling of a Korean music video has become a battlefield on which meanings are poached through punning in the process of translation. It contextualises Korean popular culture as one of the dominant genres in Taiwan and introduces ‘Sorry Sorry,’ a chart topper by Super Junior. In the specific social, cultural, p...

Foreign language (FL) films with subtitles are becoming increasingly popular, and many European countries use subtitling as a cheaper alternative to dubbing. However, the extent to which people process subtitles under different subtitling conditions remains unclear. In this study, participants watched part of a film under standard (FL soundtrack and native language subtitles), reversed (native ...