Data-driven approaches to sentence compression define the task as dropping any subset of words from the input sentence while retaining important information and grammaticality. We show that only 16% of the observed compressed sentences in the domain of subtitling can be accounted for in this way. We argue that this is partly due to the lack of appropriate evaluation material and estimate that a...

In this paper, we present the main features of the Amara project, and its impact on the accessibility landscape with the use of innovative technology. We also show the effectiveness of volunteer communities in addressing large subtitling and translation tasks, that accompany the ever-growing amounts of online video content. Furthermore, we present two different applications for the platform. Fi...

This paper investigates sentence compression for automatic subtitle generation using supervised machine learning. We present a method for sentence compression as well as discuss generation of training data from compressed Finnish sentences, and different approaches to the problem. The method we present outperforms state-of-the-art baseline in both automatic and human evaluation. On real data, 4...

Recent explosion towards 3D content-enabled devices has brought to light many issues regarding user comfort, depth perception and accessibility in media. One important element that touches these areas is subtitling. We define a pipeline to produce extruded texts for evaluating3D subtitling properties (using traditional 2D depth cues). An evaluation of current 3D tools was carried out, and the c...

Subtitling of video contents offered in the web by Spanish administration agencies is required by law for allowing people with hearing impairments to follow them. The automatic bilingual video subtitling system described in this paper has been applied on the plenary sessions videos that the Basque Parliament posts in its web (http://www.parlamentovasco.euskolegebiltzarra.org/), and is running f...

To investigate the effects of different glossing conventions on vocabulary recognition and recall, 158 participants were given a pre-test to make sure that they did not have any prior knowledge of the target words. Reading passages with four different glossing conventions (interlinear, marginal, pre-text, and post-text) were given to eight groups. Four groups received interlingual glosses and f...

We introduce a new method of sign language subtitling aimed at young deaf children who have not acquired reading skills yet, and can communicate only via signs. The method is based on: 1) the recently developed concept of “semantroidTM” (an animated 3D avatar limited to head and hands); 2) the design, development, and psychophysical evaluation of a highly comprehensible model of the semantroid;...