@inproceedings{lee-etal-2019-transformer,
title = "Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder",
author = "Lee, WonKee and
Shin, Jaehun and
Lee, Jong-Hyeok",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5412",
doi = "10.18653/v1/W19-5412",
pages = "112--117",
abstract = "This paper describes POSTECH{'}s submission to the WMT 2019 shared task on Automatic Post-Editing (APE). In this paper, we propose a new multi-source APE model by extending Transformer. The main contributions of our study are that we 1) reconstruct the encoder to generate a joint representation of translation (mt) and its src context, in addition to the conventional src encoding and 2) suggest two types of multi-source attention layers to compute attention between two outputs of the encoder and the decoder state in the decoder. Furthermore, we train our model by applying various teacher-forcing ratios to alleviate exposure bias. Finally, we adopt the ensemble technique across variations of our model. Experiments on the WMT19 English-German APE data set show improvements in terms of both TER and BLEU scores over the baseline. Our primary submission achieves -0.73 in TER and +1.49 in BLEU compare to the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2019-transformer">
<titleInfo>
<title>Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder</title>
</titleInfo>
<name type="personal">
<namePart type="given">WonKee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehun</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong-Hyeok</namePart>
<namePart type="family">Lee</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 3: Shared Task Papers, Day 2)</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>This paper describes POSTECH’s submission to the WMT 2019 shared task on Automatic Post-Editing (APE). In this paper, we propose a new multi-source APE model by extending Transformer. The main contributions of our study are that we 1) reconstruct the encoder to generate a joint representation of translation (mt) and its src context, in addition to the conventional src encoding and 2) suggest two types of multi-source attention layers to compute attention between two outputs of the encoder and the decoder state in the decoder. Furthermore, we train our model by applying various teacher-forcing ratios to alleviate exposure bias. Finally, we adopt the ensemble technique across variations of our model. Experiments on the WMT19 English-German APE data set show improvements in terms of both TER and BLEU scores over the baseline. Our primary submission achieves -0.73 in TER and +1.49 in BLEU compare to the baseline.</abstract>
<identifier type="citekey">lee-etal-2019-transformer</identifier>
<identifier type="doi">10.18653/v1/W19-5412</identifier>
<location>
<url>https://aclanthology.org/W19-5412</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>112</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder
%A Lee, WonKee
%A Shin, Jaehun
%A Lee, Jong-Hyeok
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F lee-etal-2019-transformer
%X This paper describes POSTECH’s submission to the WMT 2019 shared task on Automatic Post-Editing (APE). In this paper, we propose a new multi-source APE model by extending Transformer. The main contributions of our study are that we 1) reconstruct the encoder to generate a joint representation of translation (mt) and its src context, in addition to the conventional src encoding and 2) suggest two types of multi-source attention layers to compute attention between two outputs of the encoder and the decoder state in the decoder. Furthermore, we train our model by applying various teacher-forcing ratios to alleviate exposure bias. Finally, we adopt the ensemble technique across variations of our model. Experiments on the WMT19 English-German APE data set show improvements in terms of both TER and BLEU scores over the baseline. Our primary submission achieves -0.73 in TER and +1.49 in BLEU compare to the baseline.
%R 10.18653/v1/W19-5412
%U https://aclanthology.org/W19-5412
%U https://doi.org/10.18653/v1/W19-5412
%P 112-117
Markdown (Informal)
[Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder](https://aclanthology.org/W19-5412) (Lee et al., 2019)
ACL