@inproceedings{rapacz-smywinski-pohl-2025-low,
title = "Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for {A}ncient {G}reek",
author = "Rapacz, Maciej and
Smywi{\'n}ski-Pohl, Aleksander",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.11/",
pages = "145--165",
abstract = "Contemporary machine translation systems prioritize fluent, natural-sounding output with flexible word ordering. In contrast, interlinear translation maintains the source text`s syntactic structure by aligning target language words directly beneath their source counterparts. Despite its importance in classical scholarship, automated approaches to interlinear translation remain understudied. We evaluated neural interlinear translation from Ancient Greek to English and Polish using four transformer-based models: two Ancient Greek-specialized (GreTa and PhilTa) and two general-purpose multilingual models (mT5-base and mT5-large). Our approach introduces novel morphological embedding layers and evaluates text preprocessing and tag set selection across 144 experimental configurations using a word-aligned parallel corpus of the Greek New Testament. Results show that morphological features through dedicated embedding layers significantly enhance translation quality, improving BLEU scores by 35{\%} (44.67 {\textrightarrow} 60.40) for English and 38{\%} (42.92 {\textrightarrow} 59.33) for Polish compared to baseline models. PhilTa achieves state-of-the-art performance for English, while mT5-large does so for Polish. Notably, PhilTa maintains stable performance using only 10{\%} of training data. Our findings challenge the assumption that modern neural architectures cannot benefit from explicit morphological annotations. While preprocessing strategies and tag set selection show minimal impact, the substantial gains from morphological embeddings demonstrate their value in low-resource scenarios."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rapacz-smywinski-pohl-2025-low">
<titleInfo>
<title>Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for Ancient Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Rapacz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Smywiński-Pohl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</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">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Contemporary machine translation systems prioritize fluent, natural-sounding output with flexible word ordering. In contrast, interlinear translation maintains the source text‘s syntactic structure by aligning target language words directly beneath their source counterparts. Despite its importance in classical scholarship, automated approaches to interlinear translation remain understudied. We evaluated neural interlinear translation from Ancient Greek to English and Polish using four transformer-based models: two Ancient Greek-specialized (GreTa and PhilTa) and two general-purpose multilingual models (mT5-base and mT5-large). Our approach introduces novel morphological embedding layers and evaluates text preprocessing and tag set selection across 144 experimental configurations using a word-aligned parallel corpus of the Greek New Testament. Results show that morphological features through dedicated embedding layers significantly enhance translation quality, improving BLEU scores by 35% (44.67 → 60.40) for English and 38% (42.92 → 59.33) for Polish compared to baseline models. PhilTa achieves state-of-the-art performance for English, while mT5-large does so for Polish. Notably, PhilTa maintains stable performance using only 10% of training data. Our findings challenge the assumption that modern neural architectures cannot benefit from explicit morphological annotations. While preprocessing strategies and tag set selection show minimal impact, the substantial gains from morphological embeddings demonstrate their value in low-resource scenarios.</abstract>
<identifier type="citekey">rapacz-smywinski-pohl-2025-low</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.11/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>145</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for Ancient Greek
%A Rapacz, Maciej
%A Smywiński-Pohl, Aleksander
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F rapacz-smywinski-pohl-2025-low
%X Contemporary machine translation systems prioritize fluent, natural-sounding output with flexible word ordering. In contrast, interlinear translation maintains the source text‘s syntactic structure by aligning target language words directly beneath their source counterparts. Despite its importance in classical scholarship, automated approaches to interlinear translation remain understudied. We evaluated neural interlinear translation from Ancient Greek to English and Polish using four transformer-based models: two Ancient Greek-specialized (GreTa and PhilTa) and two general-purpose multilingual models (mT5-base and mT5-large). Our approach introduces novel morphological embedding layers and evaluates text preprocessing and tag set selection across 144 experimental configurations using a word-aligned parallel corpus of the Greek New Testament. Results show that morphological features through dedicated embedding layers significantly enhance translation quality, improving BLEU scores by 35% (44.67 → 60.40) for English and 38% (42.92 → 59.33) for Polish compared to baseline models. PhilTa achieves state-of-the-art performance for English, while mT5-large does so for Polish. Notably, PhilTa maintains stable performance using only 10% of training data. Our findings challenge the assumption that modern neural architectures cannot benefit from explicit morphological annotations. While preprocessing strategies and tag set selection show minimal impact, the substantial gains from morphological embeddings demonstrate their value in low-resource scenarios.
%U https://aclanthology.org/2025.loreslm-1.11/
%P 145-165
Markdown (Informal)
[Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for Ancient Greek](https://aclanthology.org/2025.loreslm-1.11/) (Rapacz & Smywiński-Pohl, LoResLM 2025)
ACL