@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://preview.aclanthology.org/ingest-nlpsi/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."
}