@inproceedings{pal-etal-2020-transference,
title = "The Transference Architecture for Automatic Post-Editing",
author = {Pal, Santanu and
Xu, Hongfei and
Herbig, Nico and
Naskar, Sudip Kumar and
Kr{\"u}ger, Antonio and
van Genabith, Josef},
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.524",
doi = "10.18653/v1/2020.coling-main.524",
pages = "5963--5974",
abstract = "In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder based neural APE approaches. A research challenge now is the search for architectures that best support the capture, preparation and provision of src and mt information and its integration with pe decisions. In this paper we present an efficient multi-encoder based APE model, called transference. Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a decoder block, but without masking for self-attention on mt, which effectively acts as second encoder combining src {--}{\textgreater} mt, and (iii) feeds this representation into a final decoder block generating pe. Our model outperforms the best performing systems by 1 BLEU point on the WMT 2016, 2017, and 2018 English{--}German APE shared tasks (PBSMT and NMT). Furthermore, the results of our model on the WMT 2019 APE task using NMT data shows a comparable performance to the state-of-the-art system. The inference time of our model is similar to the vanilla transformer-based NMT system although our model deals with two separate encoders. We further investigate the importance of our newly introduced second encoder and find that a too small amount of layers does hurt the performance, while reducing the number of layers of the decoder does not matter much.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-etal-2020-transference">
<titleInfo>
<title>The Transference Architecture for Automatic Post-Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santanu</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nico</namePart>
<namePart type="family">Herbig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Krüger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder based neural APE approaches. A research challenge now is the search for architectures that best support the capture, preparation and provision of src and mt information and its integration with pe decisions. In this paper we present an efficient multi-encoder based APE model, called transference. Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a decoder block, but without masking for self-attention on mt, which effectively acts as second encoder combining src –\textgreater mt, and (iii) feeds this representation into a final decoder block generating pe. Our model outperforms the best performing systems by 1 BLEU point on the WMT 2016, 2017, and 2018 English–German APE shared tasks (PBSMT and NMT). Furthermore, the results of our model on the WMT 2019 APE task using NMT data shows a comparable performance to the state-of-the-art system. The inference time of our model is similar to the vanilla transformer-based NMT system although our model deals with two separate encoders. We further investigate the importance of our newly introduced second encoder and find that a too small amount of layers does hurt the performance, while reducing the number of layers of the decoder does not matter much.</abstract>
<identifier type="citekey">pal-etal-2020-transference</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.524</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.524</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5963</start>
<end>5974</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Transference Architecture for Automatic Post-Editing
%A Pal, Santanu
%A Xu, Hongfei
%A Herbig, Nico
%A Naskar, Sudip Kumar
%A Krüger, Antonio
%A van Genabith, Josef
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F pal-etal-2020-transference
%X In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder based neural APE approaches. A research challenge now is the search for architectures that best support the capture, preparation and provision of src and mt information and its integration with pe decisions. In this paper we present an efficient multi-encoder based APE model, called transference. Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a decoder block, but without masking for self-attention on mt, which effectively acts as second encoder combining src –\textgreater mt, and (iii) feeds this representation into a final decoder block generating pe. Our model outperforms the best performing systems by 1 BLEU point on the WMT 2016, 2017, and 2018 English–German APE shared tasks (PBSMT and NMT). Furthermore, the results of our model on the WMT 2019 APE task using NMT data shows a comparable performance to the state-of-the-art system. The inference time of our model is similar to the vanilla transformer-based NMT system although our model deals with two separate encoders. We further investigate the importance of our newly introduced second encoder and find that a too small amount of layers does hurt the performance, while reducing the number of layers of the decoder does not matter much.
%R 10.18653/v1/2020.coling-main.524
%U https://aclanthology.org/2020.coling-main.524
%U https://doi.org/10.18653/v1/2020.coling-main.524
%P 5963-5974
Markdown (Informal)
[The Transference Architecture for Automatic Post-Editing](https://aclanthology.org/2020.coling-main.524) (Pal et al., COLING 2020)
ACL
- Santanu Pal, Hongfei Xu, Nico Herbig, Sudip Kumar Naskar, Antonio Krüger, and Josef van Genabith. 2020. The Transference Architecture for Automatic Post-Editing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5963–5974, Barcelona, Spain (Online). International Committee on Computational Linguistics.