@inproceedings{nakhle-etal-2026-flipper,
title = "Flipper: An Extended Document-Level Financial Dataset for Training and Evaluation with Annotated Discourse Phenomena",
author = "Nakhl{\'e}, Mariam and
Atherly, Rachel and
Gonzalez Saez, Gabriela nicole and
Dinarelli, Marco and
Qader, Raheel and
Blanchon, Herv{\'e}",
editor = "El-Haj, Mo and
Moreno Sandoval, Antonio and
Garcia-Serrano, Ana and
Chen, Chung-Chi and
Rayson, Paul and
Torterolo Orta, Yanco Amor and
Martinez, Paloma and
Porta, Jordi",
booktitle = "The 7th Financial Narrative Processing Workshop",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.fnp-1.7/",
doi = "10.63317/22f2djwbns96",
pages = "78--86",
abstract = "We present a new resource for Machine Translation (MT), namely a training and evaluation dataset containing parallel sections issued from authentic documents in the financial domain. We cover five language pairs: English-French, English-Spanish, English-German, English-Italian and French-Spanish. The total number of parallel sections is 122k and the number of tokens is 118M (source and target combined). MT has improved greatly in recent years, but certain phenomena still cause errors, particularly when context spans beyond a single sentence. Errors can lead to mistranslated pronouns, incorrect gender or number agreement, and inconsistent terminology, which can be especially problematic in high-stakes domains like finance. We therefore construct the dataset at document level (rather than sentence-level alignment) and also produce fine-grained annotations of context-sensitive phenomena. The annotation was performed using preexisting tools and custom scripts. The annotated phenomena are: formality, gender, terminology consistency, verb form and sentence reordering. This aims to improve document-level evaluation of MT models by enabling evaluation solely on texts containing a particular phenomenon of interest. Our primary contribution is the creation and public release of Flipper, a multilingual document-level parallel dataset in the financial domain, designed to support both training and targeted evaluation of context-sensitive machine translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakhle-etal-2026-flipper">
<titleInfo>
<title>Flipper: An Extended Document-Level Financial Dataset for Training and Evaluation with Annotated Discourse Phenomena</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Nakhlé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Atherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriela</namePart>
<namePart type="given">nicole</namePart>
<namePart type="family">Gonzalez Saez</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">Hervé</namePart>
<namePart type="family">Blanchon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Financial Narrative Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Garcia-Serrano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanco</namePart>
<namePart type="given">Amor</namePart>
<namePart type="family">Torterolo Orta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordi</namePart>
<namePart type="family">Porta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new resource for Machine Translation (MT), namely a training and evaluation dataset containing parallel sections issued from authentic documents in the financial domain. We cover five language pairs: English-French, English-Spanish, English-German, English-Italian and French-Spanish. The total number of parallel sections is 122k and the number of tokens is 118M (source and target combined). MT has improved greatly in recent years, but certain phenomena still cause errors, particularly when context spans beyond a single sentence. Errors can lead to mistranslated pronouns, incorrect gender or number agreement, and inconsistent terminology, which can be especially problematic in high-stakes domains like finance. We therefore construct the dataset at document level (rather than sentence-level alignment) and also produce fine-grained annotations of context-sensitive phenomena. The annotation was performed using preexisting tools and custom scripts. The annotated phenomena are: formality, gender, terminology consistency, verb form and sentence reordering. This aims to improve document-level evaluation of MT models by enabling evaluation solely on texts containing a particular phenomenon of interest. Our primary contribution is the creation and public release of Flipper, a multilingual document-level parallel dataset in the financial domain, designed to support both training and targeted evaluation of context-sensitive machine translation.</abstract>
<identifier type="citekey">nakhle-etal-2026-flipper</identifier>
<identifier type="doi">10.63317/22f2djwbns96</identifier>
<location>
<url>https://aclanthology.org/2026.fnp-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>78</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Flipper: An Extended Document-Level Financial Dataset for Training and Evaluation with Annotated Discourse Phenomena
%A Nakhlé, Mariam
%A Atherly, Rachel
%A Gonzalez Saez, Gabriela nicole
%A Dinarelli, Marco
%A Qader, Raheel
%A Blanchon, Hervé
%Y El-Haj, Mo
%Y Moreno Sandoval, Antonio
%Y Garcia-Serrano, Ana
%Y Chen, Chung-Chi
%Y Rayson, Paul
%Y Torterolo Orta, Yanco Amor
%Y Martinez, Paloma
%Y Porta, Jordi
%S The 7th Financial Narrative Processing Workshop
%D 2026
%8 May
%I European Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F nakhle-etal-2026-flipper
%X We present a new resource for Machine Translation (MT), namely a training and evaluation dataset containing parallel sections issued from authentic documents in the financial domain. We cover five language pairs: English-French, English-Spanish, English-German, English-Italian and French-Spanish. The total number of parallel sections is 122k and the number of tokens is 118M (source and target combined). MT has improved greatly in recent years, but certain phenomena still cause errors, particularly when context spans beyond a single sentence. Errors can lead to mistranslated pronouns, incorrect gender or number agreement, and inconsistent terminology, which can be especially problematic in high-stakes domains like finance. We therefore construct the dataset at document level (rather than sentence-level alignment) and also produce fine-grained annotations of context-sensitive phenomena. The annotation was performed using preexisting tools and custom scripts. The annotated phenomena are: formality, gender, terminology consistency, verb form and sentence reordering. This aims to improve document-level evaluation of MT models by enabling evaluation solely on texts containing a particular phenomenon of interest. Our primary contribution is the creation and public release of Flipper, a multilingual document-level parallel dataset in the financial domain, designed to support both training and targeted evaluation of context-sensitive machine translation.
%R 10.63317/22f2djwbns96
%U https://aclanthology.org/2026.fnp-1.7/
%U https://doi.org/10.63317/22f2djwbns96
%P 78-86
Markdown (Informal)
[Flipper: An Extended Document-Level Financial Dataset for Training and Evaluation with Annotated Discourse Phenomena](https://aclanthology.org/2026.fnp-1.7/) (Nakhlé et al., FNP 2026)
ACL