@inproceedings{torterolo-orta-etal-2026-translategemma,
title = "{T}ranslate{G}emma for {ES}-{EN} Financial Reports: Exploring Adaptability to Variable-Sized Contexts",
author = "Torterolo Orta, Yanco Amor and
Chatzi, Melina and
Moreno-Sandoval, Antonio",
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-1.8/",
doi = "10.63317/4mfhxunsaksk",
pages = "87--97",
abstract = "This paper explores bidirectional financial Machine Translation (MT) between Spanish and English, focusing on the specialized domain of annual reports from IBEX 35 companies. Fine-tuned models are compared against zero-shot scenarios through a series of experiments, testing factors such as prompting strategies and model size. On the one hand, this work studies a combination of existing fine-tuning strategies aimed at improving the adaptability of MT models to variable-sized contexts, and, on the other hand, it analyzes the limitations detected in current evaluation metrics. Results are mixed: fine-tuned models show an improvement in both short and long-context scenarios in traditional metrics, while zero-shot predictions are clearly favored by neural metrics. In fact, reference-free assessment of the source and the human reference received worse scores than the off-the-shelf prediction models. Consequently, fine-tuning on the human-made dataset hardly improves the neural metrics against zero-shot generations. This suggests that neural metrics tend to favor the fluency of MT generations and literalness over creativity, among other technical limitations regarding long-context adaptability. From a practical standpoint, the low Translation Edit Rate (TER) scores suggest that specialized fine-tuning remains the most viable path for companies to implement efficient Machine Translation Post-Editing (MTPE) workflows, given the stylistic alignment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="torterolo-orta-etal-2026-translategemma">
<titleInfo>
<title>TranslateGemma for ES-EN Financial Reports: Exploring Adaptability to Variable-Sized Contexts</title>
</titleInfo>
<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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melina</namePart>
<namePart type="family">Chatzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno-Sandoval</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>This paper explores bidirectional financial Machine Translation (MT) between Spanish and English, focusing on the specialized domain of annual reports from IBEX 35 companies. Fine-tuned models are compared against zero-shot scenarios through a series of experiments, testing factors such as prompting strategies and model size. On the one hand, this work studies a combination of existing fine-tuning strategies aimed at improving the adaptability of MT models to variable-sized contexts, and, on the other hand, it analyzes the limitations detected in current evaluation metrics. Results are mixed: fine-tuned models show an improvement in both short and long-context scenarios in traditional metrics, while zero-shot predictions are clearly favored by neural metrics. In fact, reference-free assessment of the source and the human reference received worse scores than the off-the-shelf prediction models. Consequently, fine-tuning on the human-made dataset hardly improves the neural metrics against zero-shot generations. This suggests that neural metrics tend to favor the fluency of MT generations and literalness over creativity, among other technical limitations regarding long-context adaptability. From a practical standpoint, the low Translation Edit Rate (TER) scores suggest that specialized fine-tuning remains the most viable path for companies to implement efficient Machine Translation Post-Editing (MTPE) workflows, given the stylistic alignment.</abstract>
<identifier type="citekey">torterolo-orta-etal-2026-translategemma</identifier>
<identifier type="doi">10.63317/4mfhxunsaksk</identifier>
<location>
<url>https://aclanthology.org/2026.fnp-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>87</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TranslateGemma for ES-EN Financial Reports: Exploring Adaptability to Variable-Sized Contexts
%A Torterolo Orta, Yanco Amor
%A Chatzi, Melina
%A Moreno-Sandoval, Antonio
%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 torterolo-orta-etal-2026-translategemma
%X This paper explores bidirectional financial Machine Translation (MT) between Spanish and English, focusing on the specialized domain of annual reports from IBEX 35 companies. Fine-tuned models are compared against zero-shot scenarios through a series of experiments, testing factors such as prompting strategies and model size. On the one hand, this work studies a combination of existing fine-tuning strategies aimed at improving the adaptability of MT models to variable-sized contexts, and, on the other hand, it analyzes the limitations detected in current evaluation metrics. Results are mixed: fine-tuned models show an improvement in both short and long-context scenarios in traditional metrics, while zero-shot predictions are clearly favored by neural metrics. In fact, reference-free assessment of the source and the human reference received worse scores than the off-the-shelf prediction models. Consequently, fine-tuning on the human-made dataset hardly improves the neural metrics against zero-shot generations. This suggests that neural metrics tend to favor the fluency of MT generations and literalness over creativity, among other technical limitations regarding long-context adaptability. From a practical standpoint, the low Translation Edit Rate (TER) scores suggest that specialized fine-tuning remains the most viable path for companies to implement efficient Machine Translation Post-Editing (MTPE) workflows, given the stylistic alignment.
%R 10.63317/4mfhxunsaksk
%U https://aclanthology.org/2026.fnp-1.8/
%U https://doi.org/10.63317/4mfhxunsaksk
%P 87-97
Markdown (Informal)
[TranslateGemma for ES-EN Financial Reports: Exploring Adaptability to Variable-Sized Contexts](https://aclanthology.org/2026.fnp-1.8/) (Torterolo Orta et al., FNP 2026)
ACL