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 ...

Statistical Machine Translation (SMT) has been successfully employed to support translation of film subtitles. We explore the integration of Constraint Grammar corpus annotations into a Swedish–Danish subtitle SMT system in the framework of factored SMT. While the usefulness of the annotations is limited with large amounts of parallel data, we show that linguistic annotations can increase the g...

After the publication of our work in BMC Cancer [1], we became aware of an omission. In the Methods section, under the subtitles "Cell lines and tissue samples for cDNA arrays" and "cDNA probe preparation" we failed to quote the original description of how the cDNA library was generated, published in the Journal Archives of Medical Research as quoted below [2]. Since this initial analysis, furt...

Supplementary section for Understanding Networked Applications: A First Course, Morgan Kaufmann, 1999. Copyright notice: Permission is granted to copy and distribute this material for educational purposes only, provided that this copyright notice remains attached. Object-oriented programming methodology is considerably more than just an object decomposition as described in Chapter 10. This sect...

We present a semi-supervised, languageand domain-independent approach to high precision sentence alignment. The key idea is to bootstrap a supervised discriminative learner from wood-standard alignments, i.e. alignments that have been automatically generated by state-ofthe-art sentence alignment tools. We deploy 3 different unsupervised sentence aligners (Opus, Hunalign, Gargantua) and 2 differ...

Domain adaptation is a major challenge for neural machine translation (NMT). Given unknown words or new domains, NMT systems tend to generate fluent translations at the expense of adequacy. We present a stack-based lattice search algorithm for NMT and show that constraining its search space with lattices generated by phrase-based machine translation (PBMT) improves robustness. We report consist...

We propose several techniques for improving statistical machine translation between closely-related languages with scarce resources. We use character-level translation trained on n-gram-character-aligned bitexts and tuned using word-level BLEU, which we further augment with character-based transliteration at the word level and combine with a word-level translation model. The evaluation on Maced...

After countless petitions and complaints from end users, live subtitling quality is slowly attracting the attention of broadcasters, regulators, industry scholars working in Media Accessibility. These stakeholders share an interest providing better subtitles, but their assessment a thorny issue. Although studies are still scarce, research undertaken so far has proven valuable identifying weakne...

The current study aimed at examining the effects of subtitled films on vocabulary development English as second language (ESL) students. To able to achieve this aim a mixed methods research design was employed. For quantitative part quasi-experimental implemented through approach. qualitative part, after treatment phase interviews were carried out with participants in experimental group. Accord...

Narrative videos usually illustrate the main content through multiple narrative information such as audios, video frames and subtitles. Existing summarization approaches rarely consider dimensional inputs, or ignore impact of shots artistic assembly when directly applied to videos. This paper introduces a multimodal-based aesthetic-guided method. Our method leverages multimodal including visual...