@inproceedings{matusov-etal-2019-customizing,
title = "Customizing Neural Machine Translation for Subtitling",
author = "Matusov, Evgeny and
Wilken, Patrick and
Georgakopoulou, Yota",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5209",
doi = "10.18653/v1/W19-5209",
pages = "82--93",
abstract = "In this work, we customized a neural machine translation system for translation of subtitles in the domain of entertainment. The neural translation model was adapted to the subtitling content and style and extended by a simple, yet effective technique for utilizing inter-sentence context for short sentences such as dialog turns. The main contribution of the paper is a novel subtitle segmentation algorithm that predicts the end of a subtitle line given the previous word-level context using a recurrent neural network learned from human segmentation decisions. This model is combined with subtitle length and duration constraints established in the subtitling industry. We conducted a thorough human evaluation with two post-editors (English-to-Spanish translation of a documentary and a sitcom). It showed a notable productivity increase of up to 37{\%} as compared to translating from scratch and significant reductions in human translation edit rate in comparison with the post-editing of the baseline non-adapted system without a learned segmentation model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matusov-etal-2019-customizing">
<titleInfo>
<title>Customizing Neural Machine Translation for Subtitling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evgeny</namePart>
<namePart type="family">Matusov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wilken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yota</namePart>
<namePart type="family">Georgakopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we customized a neural machine translation system for translation of subtitles in the domain of entertainment. The neural translation model was adapted to the subtitling content and style and extended by a simple, yet effective technique for utilizing inter-sentence context for short sentences such as dialog turns. The main contribution of the paper is a novel subtitle segmentation algorithm that predicts the end of a subtitle line given the previous word-level context using a recurrent neural network learned from human segmentation decisions. This model is combined with subtitle length and duration constraints established in the subtitling industry. We conducted a thorough human evaluation with two post-editors (English-to-Spanish translation of a documentary and a sitcom). It showed a notable productivity increase of up to 37% as compared to translating from scratch and significant reductions in human translation edit rate in comparison with the post-editing of the baseline non-adapted system without a learned segmentation model.</abstract>
<identifier type="citekey">matusov-etal-2019-customizing</identifier>
<identifier type="doi">10.18653/v1/W19-5209</identifier>
<location>
<url>https://aclanthology.org/W19-5209</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>82</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Customizing Neural Machine Translation for Subtitling
%A Matusov, Evgeny
%A Wilken, Patrick
%A Georgakopoulou, Yota
%S Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F matusov-etal-2019-customizing
%X In this work, we customized a neural machine translation system for translation of subtitles in the domain of entertainment. The neural translation model was adapted to the subtitling content and style and extended by a simple, yet effective technique for utilizing inter-sentence context for short sentences such as dialog turns. The main contribution of the paper is a novel subtitle segmentation algorithm that predicts the end of a subtitle line given the previous word-level context using a recurrent neural network learned from human segmentation decisions. This model is combined with subtitle length and duration constraints established in the subtitling industry. We conducted a thorough human evaluation with two post-editors (English-to-Spanish translation of a documentary and a sitcom). It showed a notable productivity increase of up to 37% as compared to translating from scratch and significant reductions in human translation edit rate in comparison with the post-editing of the baseline non-adapted system without a learned segmentation model.
%R 10.18653/v1/W19-5209
%U https://aclanthology.org/W19-5209
%U https://doi.org/10.18653/v1/W19-5209
%P 82-93
Markdown (Informal)
[Customizing Neural Machine Translation for Subtitling](https://aclanthology.org/W19-5209) (Matusov et al., 2019)
ACL
- Evgeny Matusov, Patrick Wilken, and Yota Georgakopoulou. 2019. Customizing Neural Machine Translation for Subtitling. In Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pages 82–93, Florence, Italy. Association for Computational Linguistics.