@inproceedings{song-etal-2025-multilingual-verbalisation,
title = "Multilingual Verbalisation of Knowledge Graphs",
author = "Song, Yifei and
Martinez, William Soto and
Nikiforovskaya, Anna and
Chapple, Evan Parker Kelly and
Gardent, Claire",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.60/",
doi = "10.18653/v1/2025.findings-emnlp.60",
pages = "1111--1162",
ISBN = "979-8-89176-335-7",
abstract = "Most work on Knowledge Graph (KG) verbalisation is monolingual leaving open the question of how to scale KG-to-Text generation to languages with varying amounts of resources. In this work, we explore KG-to-Text generation on nine languages including five high-resource (HR) languages (English, Chinese, French, Spanish, Russian) and four low-resource (LR) languages (Breton, Irish, Maltese, Welsh). We first construct silver multilingual training data for all nine languages and new gold out-of-domain test data for the five HR languages. Using this data and already available in-domain test sets for 7 of our 9 languages, we then compare three strategies: (1) NLG+MT{---}a state-of-the-art KG-to-English model followed by Machine Translation (MT) into the target language; (2) FTMT{---}multilingual MT models fine-tuned end-to-end on the silver data; and (3) FewShot{---}few-shot LLM prompting comparing 4 LLMs. We explore different prompting strategies and show that our best prompting strategy performs the best on all 9 languages, discussing the relative performance of the three approaches on Low vs High Resource languages and on in- vs out-of-domain data.The models, the test set, and the silver training data are available at https://github.com/MeloS7/Multilingual-KG-Verbalisation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2025-multilingual-verbalisation">
<titleInfo>
<title>Multilingual Verbalisation of Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Soto</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Nikiforovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evan</namePart>
<namePart type="given">Parker</namePart>
<namePart type="given">Kelly</namePart>
<namePart type="family">Chapple</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Most work on Knowledge Graph (KG) verbalisation is monolingual leaving open the question of how to scale KG-to-Text generation to languages with varying amounts of resources. In this work, we explore KG-to-Text generation on nine languages including five high-resource (HR) languages (English, Chinese, French, Spanish, Russian) and four low-resource (LR) languages (Breton, Irish, Maltese, Welsh). We first construct silver multilingual training data for all nine languages and new gold out-of-domain test data for the five HR languages. Using this data and already available in-domain test sets for 7 of our 9 languages, we then compare three strategies: (1) NLG+MT—a state-of-the-art KG-to-English model followed by Machine Translation (MT) into the target language; (2) FTMT—multilingual MT models fine-tuned end-to-end on the silver data; and (3) FewShot—few-shot LLM prompting comparing 4 LLMs. We explore different prompting strategies and show that our best prompting strategy performs the best on all 9 languages, discussing the relative performance of the three approaches on Low vs High Resource languages and on in- vs out-of-domain data.The models, the test set, and the silver training data are available at https://github.com/MeloS7/Multilingual-KG-Verbalisation.</abstract>
<identifier type="citekey">song-etal-2025-multilingual-verbalisation</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.60</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.60/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1111</start>
<end>1162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Verbalisation of Knowledge Graphs
%A Song, Yifei
%A Martinez, William Soto
%A Nikiforovskaya, Anna
%A Chapple, Evan Parker Kelly
%A Gardent, Claire
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F song-etal-2025-multilingual-verbalisation
%X Most work on Knowledge Graph (KG) verbalisation is monolingual leaving open the question of how to scale KG-to-Text generation to languages with varying amounts of resources. In this work, we explore KG-to-Text generation on nine languages including five high-resource (HR) languages (English, Chinese, French, Spanish, Russian) and four low-resource (LR) languages (Breton, Irish, Maltese, Welsh). We first construct silver multilingual training data for all nine languages and new gold out-of-domain test data for the five HR languages. Using this data and already available in-domain test sets for 7 of our 9 languages, we then compare three strategies: (1) NLG+MT—a state-of-the-art KG-to-English model followed by Machine Translation (MT) into the target language; (2) FTMT—multilingual MT models fine-tuned end-to-end on the silver data; and (3) FewShot—few-shot LLM prompting comparing 4 LLMs. We explore different prompting strategies and show that our best prompting strategy performs the best on all 9 languages, discussing the relative performance of the three approaches on Low vs High Resource languages and on in- vs out-of-domain data.The models, the test set, and the silver training data are available at https://github.com/MeloS7/Multilingual-KG-Verbalisation.
%R 10.18653/v1/2025.findings-emnlp.60
%U https://aclanthology.org/2025.findings-emnlp.60/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.60
%P 1111-1162
Markdown (Informal)
[Multilingual Verbalisation of Knowledge Graphs](https://aclanthology.org/2025.findings-emnlp.60/) (Song et al., Findings 2025)
ACL
- Yifei Song, William Soto Martinez, Anna Nikiforovskaya, Evan Parker Kelly Chapple, and Claire Gardent. 2025. Multilingual Verbalisation of Knowledge Graphs. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 1111–1162, Suzhou, China. Association for Computational Linguistics.