@inproceedings{clematide-etal-2026-cross,
title = "Cross-Lingual Abstractive Keyphrase Generation for Historical Newspapers",
author = "Clematide, Simon and
Meyer, Jenifer L. and
Opitz, Juri and
Ehrmann, Maud and
Beelen, Kaspar",
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.23/",
doi = "10.63317/2qijz2a9nwpd",
pages = "218--223",
abstract = "We investigate large language models (LLMs) for cross-lingual abstractive keyphrase generation from historical newspapers. The task consists of producing a small set of English keyphrases for articles written in German, French, and Luxembourgish, combining translation, abstraction, and normalization. We conduct a human-centered pilot study comparing model outputs using human selections, LLM-as-judge assessments, and inter-annotator agreement analysis, followed by a medium-scale application to multilingual data from the Impresso corpus. Results show that LLM-generated keyphrases can support semantic enrichment and exploratory analysis of historical collections, while highlighting the subjective and methodologically challenging nature of keyphrase evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clematide-etal-2026-cross">
<titleInfo>
<title>Cross-Lingual Abstractive Keyphrase Generation for Historical Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenifer</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maud</namePart>
<namePart type="family">Ehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaspar</namePart>
<namePart type="family">Beelen</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>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA 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 investigate large language models (LLMs) for cross-lingual abstractive keyphrase generation from historical newspapers. The task consists of producing a small set of English keyphrases for articles written in German, French, and Luxembourgish, combining translation, abstraction, and normalization. We conduct a human-centered pilot study comparing model outputs using human selections, LLM-as-judge assessments, and inter-annotator agreement analysis, followed by a medium-scale application to multilingual data from the Impresso corpus. Results show that LLM-generated keyphrases can support semantic enrichment and exploratory analysis of historical collections, while highlighting the subjective and methodologically challenging nature of keyphrase evaluation.</abstract>
<identifier type="citekey">clematide-etal-2026-cross</identifier>
<identifier type="doi">10.63317/2qijz2a9nwpd</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.23/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>218</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Abstractive Keyphrase Generation for Historical Newspapers
%A Clematide, Simon
%A Meyer, Jenifer L.
%A Opitz, Juri
%A Ehrmann, Maud
%A Beelen, Kaspar
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F clematide-etal-2026-cross
%X We investigate large language models (LLMs) for cross-lingual abstractive keyphrase generation from historical newspapers. The task consists of producing a small set of English keyphrases for articles written in German, French, and Luxembourgish, combining translation, abstraction, and normalization. We conduct a human-centered pilot study comparing model outputs using human selections, LLM-as-judge assessments, and inter-annotator agreement analysis, followed by a medium-scale application to multilingual data from the Impresso corpus. Results show that LLM-generated keyphrases can support semantic enrichment and exploratory analysis of historical collections, while highlighting the subjective and methodologically challenging nature of keyphrase evaluation.
%R 10.63317/2qijz2a9nwpd
%U https://aclanthology.org/2026.llms4ssh-1.23/
%U https://doi.org/10.63317/2qijz2a9nwpd
%P 218-223
Markdown (Informal)
[Cross-Lingual Abstractive Keyphrase Generation for Historical Newspapers](https://aclanthology.org/2026.llms4ssh-1.23/) (Clematide et al., LLMs4SSH 2026)
ACL
- Simon Clematide, Jenifer L. Meyer, Juri Opitz, Maud Ehrmann, and Kaspar Beelen. 2026. Cross-Lingual Abstractive Keyphrase Generation for Historical Newspapers. In Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026, pages 218–223, Palma de Mallorca (Spain). ELRA Language Resources Association (ELRA).