@inproceedings{lopez-etal-2023-make,
title = "The {MAKE}-{NMTVIZ} System Description for the {WMT}23 Literary Task",
author = "Lopez, Fabien and
Gonz{\'a}lez, Gabriela and
Hansen, Damien and
Nakhle, Mariam and
Namdarzadeh, Behnoosh and
Ballier, Nicolas and
Dinarelli, Marco and
Esperan{\c{c}}a-Rodier, Emmanuelle and
He, Sui and
Mohseni, Sadaf and
Rossi, Caroline and
Schwab, Didier and
Yang, Jun and
Yun{\`e}s, Jean-Baptiste and
Zhu, Lichao",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.30",
doi = "10.18653/v1/2023.wmt-1.30",
pages = "287--295",
abstract = "This paper describes the MAKE-NMTVIZ Systems trained for the WMT 2023 Literary task. As a primary submission, we used Train, Valid1, test1 as part of the GuoFeng corpus (Wang et al., 2023) to fine-tune the mBART50 model with Chinese-English data. We followed very similar training parameters to (Lee et al. 2022) when fine-tuning mBART50. We trained for 3 epochs, using gelu as an activation function, with a learning rate of 0.05, dropout of 0.1 and a batch size of 16. We decoded using a beam search of size 5. For our contrastive1 submission, we implemented a fine-tuned concatenation transformer (Lupo et al., 2023). The training was developed in two steps: (i) a sentence-level transformer was implemented for 10 epochs trained using general, test1, and valid1 data (more details in contrastive2 system); (ii) second, we fine-tuned at document-level using 3-sentence concatenation for 4 epochs using train, test2, and valid2 data. During the fine-tuning, we used ReLU as an activation function, with an inverse square root learning rate, dropout of 0.1, and a batch size of 64. We decoded using a beam search of size. Four our contrastive2 and last submission, we implemented a sentence-level transformer model (Vaswani et al., 2017). The model was trained with general data for 10 epochs using general-purpose, test1, and valid 1 data. The training parameters were an inverse square root scheduled learning rate, a dropout of 0.1, and a batch size of 64. We decoded using a beam search of size 4. We then compared the three translation outputs from an interdisciplinary perspective, investigating some of the effects of sentence- vs document-based training. Computer scientists, translators and corpus linguists discussed the linguistic remaining issues for this discourse-level literary translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-etal-2023-make">
<titleInfo>
<title>The MAKE-NMTVIZ System Description for the WMT23 Literary Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabien</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriela</namePart>
<namePart type="family">González</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Nakhle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnoosh</namePart>
<namePart type="family">Namdarzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Ballier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Dinarelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuelle</namePart>
<namePart type="family">Esperança-Rodier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sui</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadaf</namePart>
<namePart type="family">Mohseni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Didier</namePart>
<namePart type="family">Schwab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Baptiste</namePart>
<namePart type="family">Yunès</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lichao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the MAKE-NMTVIZ Systems trained for the WMT 2023 Literary task. As a primary submission, we used Train, Valid1, test1 as part of the GuoFeng corpus (Wang et al., 2023) to fine-tune the mBART50 model with Chinese-English data. We followed very similar training parameters to (Lee et al. 2022) when fine-tuning mBART50. We trained for 3 epochs, using gelu as an activation function, with a learning rate of 0.05, dropout of 0.1 and a batch size of 16. We decoded using a beam search of size 5. For our contrastive1 submission, we implemented a fine-tuned concatenation transformer (Lupo et al., 2023). The training was developed in two steps: (i) a sentence-level transformer was implemented for 10 epochs trained using general, test1, and valid1 data (more details in contrastive2 system); (ii) second, we fine-tuned at document-level using 3-sentence concatenation for 4 epochs using train, test2, and valid2 data. During the fine-tuning, we used ReLU as an activation function, with an inverse square root learning rate, dropout of 0.1, and a batch size of 64. We decoded using a beam search of size. Four our contrastive2 and last submission, we implemented a sentence-level transformer model (Vaswani et al., 2017). The model was trained with general data for 10 epochs using general-purpose, test1, and valid 1 data. The training parameters were an inverse square root scheduled learning rate, a dropout of 0.1, and a batch size of 64. We decoded using a beam search of size 4. We then compared the three translation outputs from an interdisciplinary perspective, investigating some of the effects of sentence- vs document-based training. Computer scientists, translators and corpus linguists discussed the linguistic remaining issues for this discourse-level literary translation.</abstract>
<identifier type="citekey">lopez-etal-2023-make</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.30</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.30</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>287</start>
<end>295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The MAKE-NMTVIZ System Description for the WMT23 Literary Task
%A Lopez, Fabien
%A González, Gabriela
%A Hansen, Damien
%A Nakhle, Mariam
%A Namdarzadeh, Behnoosh
%A Ballier, Nicolas
%A Dinarelli, Marco
%A Esperança-Rodier, Emmanuelle
%A He, Sui
%A Mohseni, Sadaf
%A Rossi, Caroline
%A Schwab, Didier
%A Yang, Jun
%A Yunès, Jean-Baptiste
%A Zhu, Lichao
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lopez-etal-2023-make
%X This paper describes the MAKE-NMTVIZ Systems trained for the WMT 2023 Literary task. As a primary submission, we used Train, Valid1, test1 as part of the GuoFeng corpus (Wang et al., 2023) to fine-tune the mBART50 model with Chinese-English data. We followed very similar training parameters to (Lee et al. 2022) when fine-tuning mBART50. We trained for 3 epochs, using gelu as an activation function, with a learning rate of 0.05, dropout of 0.1 and a batch size of 16. We decoded using a beam search of size 5. For our contrastive1 submission, we implemented a fine-tuned concatenation transformer (Lupo et al., 2023). The training was developed in two steps: (i) a sentence-level transformer was implemented for 10 epochs trained using general, test1, and valid1 data (more details in contrastive2 system); (ii) second, we fine-tuned at document-level using 3-sentence concatenation for 4 epochs using train, test2, and valid2 data. During the fine-tuning, we used ReLU as an activation function, with an inverse square root learning rate, dropout of 0.1, and a batch size of 64. We decoded using a beam search of size. Four our contrastive2 and last submission, we implemented a sentence-level transformer model (Vaswani et al., 2017). The model was trained with general data for 10 epochs using general-purpose, test1, and valid 1 data. The training parameters were an inverse square root scheduled learning rate, a dropout of 0.1, and a batch size of 64. We decoded using a beam search of size 4. We then compared the three translation outputs from an interdisciplinary perspective, investigating some of the effects of sentence- vs document-based training. Computer scientists, translators and corpus linguists discussed the linguistic remaining issues for this discourse-level literary translation.
%R 10.18653/v1/2023.wmt-1.30
%U https://aclanthology.org/2023.wmt-1.30
%U https://doi.org/10.18653/v1/2023.wmt-1.30
%P 287-295
Markdown (Informal)
[The MAKE-NMTVIZ System Description for the WMT23 Literary Task](https://aclanthology.org/2023.wmt-1.30) (Lopez et al., WMT 2023)
ACL
- Fabien Lopez, Gabriela González, Damien Hansen, Mariam Nakhle, Behnoosh Namdarzadeh, Nicolas Ballier, Marco Dinarelli, Emmanuelle Esperança-Rodier, Sui He, Sadaf Mohseni, Caroline Rossi, Didier Schwab, Jun Yang, Jean-Baptiste Yunès, and Lichao Zhu. 2023. The MAKE-NMTVIZ System Description for the WMT23 Literary Task. In Proceedings of the Eighth Conference on Machine Translation, pages 287–295, Singapore. Association for Computational Linguistics.