GePpeTto Carves Italian into a Language Model

Lorenzo De Mattei, Michele Cafagna, Felice Dell'Orletta, Malvina Nissim, Marco Guerini

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    12 Downloads (Pure)


    In the last few years, pre-trained neural architectures have provided impressive improvements across several NLP tasks. Still, generative language models are available mainly for English. We develop GePpeTto, the first generative language model for Italian, built using the GPT-2 architecture. We provide a thorough analysis of GePpeTto’s quality by means of both an automatic and a human-based evaluation. The automatic assessment consists in (i) calculating perplexity across different genres and (ii) a profiling analysis over GePpeTto’s writing characteristics. We find that GePpeTto’s production is a sort of bonsai version of human production, with shorter but yet complex sentences. Human evaluation is performed over a sentence completion task, where GePpeTto’s output is judged as natural more often than not, and much closer to the original human texts than to a simpler language model which we take as baseline.

    Original languageEnglish
    Title of host publicationProceedings of the Seventh Italian Conference on Computational Linguistics, CLiC-it 2020, Bologna, Italy, March 1-3, 2021
    EditorsJohanna Monti, Felice Dell'Orletta, Fabio Tamburini
    Number of pages8
    Publication statusPublished - 2020
    EventItalian Conference on Computational Linguistics 2020 - Bologna, Italy
    Duration: 1-Mar-20213-Mar-2021


    ConferenceItalian Conference on Computational Linguistics 2020
    Abbreviated titleCLiC-it 2020

    Cite this