@inproceedings{an-etal-2023-max,
title = "{MAX}-{ISI} System at {WMT}23 Discourse-Level Literary Translation Task",
author = "An, Li and
Jin, Linghao and
Ma, Xuezhe",
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-1.29",
doi = "10.18653/v1/2023.wmt-1.29",
pages = "282--286",
abstract = "This paper describes our translation systems for the WMT23 shared task. We participated in the discourse-level literary translation task - constrained track. In our methodology, we conduct a comparative analysis between the conventional Transformer model and the recently introduced MEGA model, which exhibits enhanced capabilities in modeling long-range sequences compared to the traditional Transformers. To explore whether language models can more effectively harness document-level context using paragraph-level data, we took the approach of aggregating sentences into paragraphs from the original literary dataset provided by the organizers. This paragraph-level data was utilized in both the Transformer and MEGA models. To ensure a fair comparison across all systems, we employed a sentence-alignment strategy to reverse our translation results from the paragraph-level back to the sentence-level alignment. Finally, our evaluation process encompassed sentence-level metrics such as BLEU, as well as two document-level metrics: d-BLEU and BlonDe.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2023-max">
<titleInfo>
<title>MAX-ISI System at WMT23 Discourse-Level Literary Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linghao</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuezhe</namePart>
<namePart type="family">Ma</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 our translation systems for the WMT23 shared task. We participated in the discourse-level literary translation task - constrained track. In our methodology, we conduct a comparative analysis between the conventional Transformer model and the recently introduced MEGA model, which exhibits enhanced capabilities in modeling long-range sequences compared to the traditional Transformers. To explore whether language models can more effectively harness document-level context using paragraph-level data, we took the approach of aggregating sentences into paragraphs from the original literary dataset provided by the organizers. This paragraph-level data was utilized in both the Transformer and MEGA models. To ensure a fair comparison across all systems, we employed a sentence-alignment strategy to reverse our translation results from the paragraph-level back to the sentence-level alignment. Finally, our evaluation process encompassed sentence-level metrics such as BLEU, as well as two document-level metrics: d-BLEU and BlonDe.</abstract>
<identifier type="citekey">an-etal-2023-max</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.29</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.29</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>282</start>
<end>286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAX-ISI System at WMT23 Discourse-Level Literary Translation Task
%A An, Li
%A Jin, Linghao
%A Ma, Xuezhe
%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 an-etal-2023-max
%X This paper describes our translation systems for the WMT23 shared task. We participated in the discourse-level literary translation task - constrained track. In our methodology, we conduct a comparative analysis between the conventional Transformer model and the recently introduced MEGA model, which exhibits enhanced capabilities in modeling long-range sequences compared to the traditional Transformers. To explore whether language models can more effectively harness document-level context using paragraph-level data, we took the approach of aggregating sentences into paragraphs from the original literary dataset provided by the organizers. This paragraph-level data was utilized in both the Transformer and MEGA models. To ensure a fair comparison across all systems, we employed a sentence-alignment strategy to reverse our translation results from the paragraph-level back to the sentence-level alignment. Finally, our evaluation process encompassed sentence-level metrics such as BLEU, as well as two document-level metrics: d-BLEU and BlonDe.
%R 10.18653/v1/2023.wmt-1.29
%U https://aclanthology.org/2023.wmt-1.29
%U https://doi.org/10.18653/v1/2023.wmt-1.29
%P 282-286
Markdown (Informal)
[MAX-ISI System at WMT23 Discourse-Level Literary Translation Task](https://aclanthology.org/2023.wmt-1.29) (An et al., WMT 2023)
ACL