@inproceedings{nakhle-etal-2025-dolfin,
title = "{DOLFIN} - Document-Level Financial Test-Set for Machine Translation",
author = "Nakhle, Mariam and
Dinarelli, Marco and
Qader, Raheel and
Esperan{\c{c}}a-Rodier, Emmanuelle and
Blanchon, Herv{\'e}",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.307/",
doi = "10.18653/v1/2025.findings-naacl.307",
pages = "5544--5556",
ISBN = "979-8-89176-195-7",
abstract = "Despite the strong research interest in document-level Machine Translation (MT), the test-sets dedicated to this task are still scarce. The existing test-sets mainly cover topics from the general domain and fall short on specialised domains, such as legal and financial. Also, despite their document-level aspect, they still follow a sentence-level logic that doesn{'}t allow for including certain linguistic phenomena such as information reorganisation. In this work, we aim to fill this gap by proposing a novel test-set : DOLFIN. The dataset is built from specialised financial documents and it makes a step towards true document-level MT by abandoning the paradigm of perfectly aligned sentences, presenting data in units of sections rather than sentences. The test-set consists of an average of 1950 aligned sections for five language pairs. We present the detailed data collection pipeline that can serve as inspiration for aligning new document-level datasets. We demonstrate the usefulness and the quality of this test-set with the evaluation of a series of models. Our results show that the test-set is able to discriminate between context-sensitive and context-agnostic models and shows the weaknesses when models fail to accurately translate financial texts. The test-set will be made public for the community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakhle-etal-2025-dolfin">
<titleInfo>
<title>DOLFIN - Document-Level Financial Test-Set for Machine Translation</title>
</titleInfo>
<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">Marco</namePart>
<namePart type="family">Dinarelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raheel</namePart>
<namePart type="family">Qader</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">Hervé</namePart>
<namePart type="family">Blanchon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Despite the strong research interest in document-level Machine Translation (MT), the test-sets dedicated to this task are still scarce. The existing test-sets mainly cover topics from the general domain and fall short on specialised domains, such as legal and financial. Also, despite their document-level aspect, they still follow a sentence-level logic that doesn’t allow for including certain linguistic phenomena such as information reorganisation. In this work, we aim to fill this gap by proposing a novel test-set : DOLFIN. The dataset is built from specialised financial documents and it makes a step towards true document-level MT by abandoning the paradigm of perfectly aligned sentences, presenting data in units of sections rather than sentences. The test-set consists of an average of 1950 aligned sections for five language pairs. We present the detailed data collection pipeline that can serve as inspiration for aligning new document-level datasets. We demonstrate the usefulness and the quality of this test-set with the evaluation of a series of models. Our results show that the test-set is able to discriminate between context-sensitive and context-agnostic models and shows the weaknesses when models fail to accurately translate financial texts. The test-set will be made public for the community.</abstract>
<identifier type="citekey">nakhle-etal-2025-dolfin</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.307</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.307/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5544</start>
<end>5556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DOLFIN - Document-Level Financial Test-Set for Machine Translation
%A Nakhle, Mariam
%A Dinarelli, Marco
%A Qader, Raheel
%A Esperança-Rodier, Emmanuelle
%A Blanchon, Hervé
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F nakhle-etal-2025-dolfin
%X Despite the strong research interest in document-level Machine Translation (MT), the test-sets dedicated to this task are still scarce. The existing test-sets mainly cover topics from the general domain and fall short on specialised domains, such as legal and financial. Also, despite their document-level aspect, they still follow a sentence-level logic that doesn’t allow for including certain linguistic phenomena such as information reorganisation. In this work, we aim to fill this gap by proposing a novel test-set : DOLFIN. The dataset is built from specialised financial documents and it makes a step towards true document-level MT by abandoning the paradigm of perfectly aligned sentences, presenting data in units of sections rather than sentences. The test-set consists of an average of 1950 aligned sections for five language pairs. We present the detailed data collection pipeline that can serve as inspiration for aligning new document-level datasets. We demonstrate the usefulness and the quality of this test-set with the evaluation of a series of models. Our results show that the test-set is able to discriminate between context-sensitive and context-agnostic models and shows the weaknesses when models fail to accurately translate financial texts. The test-set will be made public for the community.
%R 10.18653/v1/2025.findings-naacl.307
%U https://aclanthology.org/2025.findings-naacl.307/
%U https://doi.org/10.18653/v1/2025.findings-naacl.307
%P 5544-5556
Markdown (Informal)
[DOLFIN - Document-Level Financial Test-Set for Machine Translation](https://aclanthology.org/2025.findings-naacl.307/) (Nakhle et al., Findings 2025)
ACL