Original papers

  • Aurora Alagni, Francesco Mambrini and Marco Passarotti.
    Lifeless winter without break: Ovid’s exile works and the LiLa Knowledge Base
  • Giorgia Albertin and Elena Martinelli.
    Exploring the Use of Cohesive Devices in Dementia within an Elderly Italian Semi-spontaneous Speech Corpus
  • Chiara Alzetta, Felice Dell’Orletta, Chiara Fazzone and Giulia Venturi.
    SimilEx: the First Italian Dataset for Sentence Similarity with Natural Language Explanations
  • Muhammad Saad Amin, Luca Anselma and Alessandro Mazzei.
    Data Augmentation for Low-Resource Italian NLP: Enhancing Semantic Processing with DRS
  • Giuseppe Attanasio, Pieter Delobelle, Moreno La Quatra, Andrea Santilli and Beatrice Savoldi.
    ItaEval and TweetyIta: A New Extensive Benchmark and Efficiency-First Language Model for Italian
  • Roberto Basile Giannini, Antonio Origlia and Maria Di Maro.
    Taking decisions in a Hybrid Conversational AI architecture using Influence Diagrams
  • Pierpaolo Basile, Marco DeGemmis, Marco Polignano, Giovanni Semeraro, Lucia Siciliani, Vincenzo Tamburrano, Fabiana Battista and Rosa Scardigno.
    LLaMAntino against Cyber Intimate Partner Violence
  • Lorenzo Bocchi and Alessio Palmero Aprosio.
    Title is (Not) All You Need for EuroVoc Multi-Label Classification of European Laws
  • Lorenzo Bocchi, Camilla Casula and Alessio Palmero Aprosio.
    KEVLAR: the Complete Resource for EuroVoc Classification of Legal Documents
  • Tommaso Bonomo, Simone Conia and Roberto Navigli.
    Exploring the Dissociated Nucleus Phenomenon in Semantic Role Labeling
  • Tom Bourgeade, Silvia Casola, Adel Mahmoud Wizan and Cristina Bosco.
    Data Augmentation through Back-Translation for Stereotypes and Irony Detection
  • Emanuele Brugnoli and Donald Ruggiero Lo Sardo.
    Community-based Stance Detection
  • Lucia Busso and Claudia Roberta Combei.
    Written Goodbyes: How Genre and Sociolinguistic Factors Influence the Content and Style of Suicide Notes
  • Jérémie Cabessa, Hugo Hernault and Umer Mushtaq.
    Argument Mining in BioMedicine: Zero-Shot, In-Context Learning and Fine-tuning with LLMs
  • Gaia Caligiore, Raffaele Mineo, Concetto Spampinato, Egidio Ragonese, Simone Palazzo and sabina fontana.
    Multisource Approaches to Italian Sign Language (LIS) Recognition: Insights from the MultiMedaLIS Dataset
  • Giulia Calvi, Riccardo Ginevra and Federica Iurescia.
    Combining Universal Dependencies and FrameNet to identify constructions in a poetic corpus: syntax and semantics of Latin felix and infelix in Virgilian poetics
  • Luca Capone, Alice Suozzi, Gianluca Lebani and Alessandro Lenci.
    BaBIEs: A Benchmark for the Linguistic Evaluation of Italian Baby Language Models
  • Luca Capone, Serena Auriemma, Martina Miliani, Alessandro Bondielli and Alessandro Lenci.
    Lost in Disambiguation: How Instruction-Tuned LLMs Master Lexical Ambiguity
  • Eleonora Cappuccio, Benedetta Muscato, Laura Pollacci, Marta Marchiori Manerba, Clara Punzi, Chandana Sree Mala, Margherita Lalli, Gizem Gezici, Michela Natilli and Fosca Giannotti.
    Beyond Headlines: A Corpus of Femicides News Coverage in Italian Newspapers
  • Alessio Cascione, Aldo Cerulli, Marta Marchiori Manerba and Lucia C. Passaro.
    Women’s Professions and Targeted Misogyny Online
  • Pierluigi Cassotti, Pierpaolo Basile and Nina Tahmasebi.
    DWUGs-IT: Extending and Standardizing Lexical Semantic Change Detection for Italian
  • Fabio Celli and Valerio Basile.
    History Repeats: Historical Phase Recognition from Short Texts
  • Francesca Chiusaroli, Federico Sangati, Johanna Monti, Maria Laura Pierucci and Tiberio Uricchio.
    Emojilingo: Harnessing AI to Translate Words into Emojis
  • Ilaria Chizzoni and Alessandro Vietti.
    Towards an ASR system for documenting endangered languages: a preliminary study on Sardinian
  • Cristiano Ciaccio, Felice Dell’Orletta, Alessio Miaschi and Giulia Venturi.
    Controllable Text Generation To Evaluate Linguistic Abilities of Italian LLMs
  • Anna Colli, Diego Rossini and Delphine BATTISTELLI.
    A modal sense classifier for the French modal verb pouvoir
  • Michele Corazza, Leonardo Zilli and Monica Palmirani.
    Topic Similarity of Heterogeneous Legal Sources Supporting the Legislative Process
  • Claudia Corbetta, Giovanni Moretti and Marco Passarotti.
    Join Together? Combining Data to Parse Italian Texts
  • Federico D’Asaro, Juan José Márquez Villacís, Giuseppe Rizzo and Andrea Bottino.
    Using Large Speech Models for Feature Extraction in Cross-Lingual Speech Emotion Recognition
  • Irene De Felice and Francesca Strik Lievers.
    Building a pragmatically annotated diachronic corpus: the DIADIta project
  • Eleonora Delfino, Roberta Leotta, Marco Passarotti and Giovanni Moretti.
    Building CorefLat. A linguistic resource for coreference and anaphora resolution in Latin
  • Chiara Di Bonaventura, Lucia Siciliani, Pierpaolo Basile, Albert Merono Penuela and Barbara McGillivray.
    Is Explanation All You Need? An Expert Survey on LLM-generated Explanations for Abusive Language Detection
  • Giuseppe Di Fabbrizio, Evgeny A. Stepanov, Ludovico Frizziero and Filippo Tessaro.
    Scalable Query Understanding for E-commerce: An Ensemble Architecture with Graph-based Optimization
  • Eliana Di Palma.
    ELIta: A New Italian Language Resource for Emotion Analysis
  • Anca Dinu and Andra Maria Florescu.
    Comparing Large Language Models verbal creativity to human verbal creativity
  • Liviu P. Dinu, Ioan-Bogdan Iordache, Simona Georgescu, Alina Maria Cristea and Bianca Guita.
    ItGraSyll: A Computational Analysis of Graphical Syllabification and Stress Assignment in Italian
  • Nicolò Donati, Matteo Periani, Paolo Di Natale, Giuseppe Savino and Paolo Torroni.
    Generation and Evaluation of English Grammar Multiple-Choice Cloze Exercises
  • Lia Draetta, Chiara Ferrando, Marco Cuccarini, Liam James and Viviana Patti.
    ReCLAIM Project: Exploring Italian Slurs Reappropriation with Large Language Models
  • Andrea Esuli, Fabrizio Falchi, Marco Malvaldi and Giovanni Puccetti.
    You write like a GPT
  • Alice Fedotova, Adriano Ferraresi, Maja Miličević Petrović and Alberto Barrón-Cedeño.
    Constructing a Multimodal, Multilingual Translation and Interpreting Corpus: A Modular Pipeline and an Evaluation of ASR for Verbatim Transcription
  • Chiara Ferrando, Marco Madeddu, Viviana Patti, Mirko Lai, Sveva Silvia Pasini, Giulia Telari and Beatrice Antola.
    Exploring YouTube Comments Reacting to Femicide News in Italian
  • Irene Fioravanti, luciana forti and Stefania Spina.
    Automatic Error Detection: Comparing AI vs. Human Performance on L2 Italian Texts
  • Dennis Fucci, Beatrice Savoldi, Marco Gaido, Matteo Negri, Mauro Cettolo and Luisa Bentivogli.
    Explainability for Speech Models: On the Challenges of Acoustic Feature Selection
  • Achille Fusco, Matilde Barbini, Maria Letizia Piccini Bianchessi, Veronica Bressan, Sofia Neri, Sarah Rossi, Tommaso Sgrizzi and Cristiano Chesi.
    Recurrent Networks are (Linguistically) Better? An (Ongoing) Experiment on Small-LM training on Child-Directed Speech in Italian
  • Paolo Gajo and Alberto Barrón-Cedeño.
    On Cross-Language Entity Label Projection and Recognition
  • Alessandro Giaconia, Valeria Chiariello and Marco Carlo Passarotti.
    Topic modeling for auditing purposes in the banking sector
  • Francesca Grasso, Ronny Patz and Manfred Stede.
    NYTAC-CC: A Climate Change Subcorpus of New York Times Articles
  • Natalia Graziuso, Andrea Zugarini and Stefano Melacci.
    Task-Incremental Learning on Long Text Sequences
  • Ibai Guillén-Pacho, Arianna Longo, Marco Antonio Stranisci, Viviana Patti and Carlos Badenes-Olmedo.
    The Vulnerable Identities Recognition Corpus (VIRC) for Hate Speech Analysis
  • Viola Gullace, David Kletz, Thierry Poibeau, Alessandro Lenci and Pascal Amsili.
    The Self-Contained Italian Negation Test (SCIN)
  • Claudiu Daniel Hromei, Danilo Croce, Rodolfo Delmonte and Roberto Basili.
    La non canonica l’hai studiata? Exploring LLMs and Sentence Canonicity in Italian
  • Hamit Kavas, Marc Serra-Vidal and Leo Wanner.
    Enhancing Job Posting Classification with Multilingual Embeddings and Large Language Models
  • Aenne Cecilia Kristine Knierim, Michael Achmann-Denkler, Ulrich Heid and Christian Wolff.
    Divergent Discourses: A Comparative Examination of Blackout Tuesday and #BlackLivesMatter on Instagram
  • Moritz Kronberger and Viviana Ventura.
    THAVQA: a German task-oriented VQA dataset annotated with human visual attention
  • Tiziano Labruna, Sofia Brenna, Giovanni Bonetta and Bernardo Magnini.
    Are you a Good Assistant? Assessing LLM Trustability in Task-oriented Dialogues
  • Alessandro Lento, Andrea Nadalini, Nadia Khlif, vito pirrelli, Claudia Marzi and Marcello Ferro.
    Comparative Evaluation of Computational Models Predicting Eye Fixation Patterns During Reading: Insights from Transformers and Simpler Architectures
  • Giulio Leonardi, Dominique Brunato and Felice Dell’Orletta.
    Hits or Misses? A Linguistically Explainable Formula for Fanfiction Success
  • Daniele Licari, Canio Benedetto, Praveen Bushipaka, Alessandro De Gregorio, Marco De Leonardis and Tommaso Cucinotta.
    A Novel Multi-Step Prompt Approach for LLM-based Q&As on Banking Supervisory Regulation
  • Livia Lilli, Laura Antenucci, Augusta Ortolan, Silvia Laura Bosello, Maria Antonietta D’Agostino, Stefano Patarnello, Carlotta Masciocchi and Jacopo Lenkowicz.
    Lupus Alberto: A Transformer-Based Approach for SLE Information Extraction from Italian Clinical Reports
  • Eleonora Litta, Marco Passarotti, Paolo Brasolin, Giovanni Moretti, Valerio Basile, Andrea Di Fabio and Cristina Bosco.
    The Lemma Bank of the LiITA Knowledge Base of Interoperable Resources for Italian
  • Sofia Lugli and Carlo Strapparava.
    Multimodal Chain-of-Thought Prompting for Metaphor Generation
  • Michele Joshua Maggini and Pablo Gamallo Otero.
    Leveraging Advanced Prompting Strategies in LLaMA3-8b for Enhanced Hyperpartisan News Detection
  • Bernardo Magnini and Roberto Zanoli.
    Understanding High-complexity Technical Documents with State-of-Art Models
  • Simone Manai, Laura Gemme, Roberto Zanoli and Alberto Lavelli.
    IDRE: AI Generated Dataset for Enhancing Empathetic Chatbot Interactions in Italian language.
  • Veronica Mangiaterra, Chiara Barattieri di San Pietro and Valentina Bambini.
    Temporal word embeddings in the study of metaphor change over time and across genres: a proof-of-concept study on English
  • Federica Manzi, Leon Weber-Genzel and Barbara Plank.
    Fine-grained Sexism Detection in Italian Newspapers
  • Luca Moroni, Simone Conia, Federico Martelli and Roberto Navigli.
    Towards a More Comprehensive Evaluation for Italian LLMs
  • Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Edoardo Michielon, Marco Pasqualini, Asia Beatrice Uboldi and Giovanni Semeraro.
    A study on the soundness of closed-ended evaluation of Large Language Models adapted to the Italian language
  • Francesca Nannetti and Matteo Di Cristofaro.
    Understanding the Future Green Workforce through a Corpus of Curricula Vitae from Recent Graduates
  • Vivi Nastase, Giuseppe Samo, Chunyang Jiang and Paola Merlo.
    Exploring Italian sentence embeddings properties through multi-tasking
  • Vivi Nastase, Giuseppe Samo, Chunyang Jiang and Paola Merlo.
    Exploring syntactic information in sentence embeddings through multilingual subject-verb agreement
  • Jan Nehring, Akhil Juneja, Adnan Ahmad, Roland Roller and Dietrich Klakow.
    Dynamic Prompting: Large Language Models for Task Oriented Dialog
  • Yuri Noviello and Fabio Tamburini.
    Exploring Text-Embedding Retrieval Models for the Italian Language
  • Laura Occhipinti.
    Introducing MultiLS-IT: A Dataset for Lexical Simplification in Italian
  • Laura Occhipinti.
    Enhancing Lexical Complexity Prediction in Italian through Automatic Morphological Segmentation
  • Dario Onorati, Davide Venditti, Elena Sofia Ruzzetti, Federico Ranaldi, Leonardo Ranaldi and Fabio Massimo Zanzotto.
    Measuring bias in Instruction-Following models with ItaP-AT for the Italian Language
  • Riccardo Orlando, Luca Moroni, ‪Pere-Lluís Huguet Cabot, Simone Conia, Edoardo Barba, Sergio Orlandini, Giuseppe Fiameni and Roberto Navigli.
    Minerva LLMs: The First Family of Large Language Models Trained from Scratch on Italian Data
  • Francesco Ortame, Mauro Bruno, Elena Catanese and Francesco Pugliese.
    Towards a Hate Speech Index with Attention-based LSTMs and BERT
  • Teresa Paccosi and Sara Tonelli.
    Benchmarking the Semantics of Taste: Towards the Automatic Extraction of Gustatory Language
  • Giada Palmieri and Konstantinos Kogkalidis.
    Nominal Class Assignment in Swahili: A Computational Account
  • Ludovica Pannitto, Lorenzo Albanesi, Laura Marion, Federica Maria Martines, Carmelo Caruso, Claudia Savina Bianchini, Francesca Masini and Caterina Mauri.
    Did somebody say ‘Gest-IT’? A pilot exploration of multimodal data management
  • Mariachiara Pascucci and Mirko Tavosanis.
    Confronto tra diversi tipi di valutazione del miglioramento della chiarezza di testi amministrativi in lingua italiana
  • Filippo Pellegrino, Jennifer Carmen Frey and Lorenzo Zanasi.
    Towards an Automatic Evaluation of (In)coherence in Student Essays
  • Fabio Pernisi, Giuseppe Attanasio and Debora Nozza.
    MONICA: Monitoring Coverage and Attitudes of Italian Measures in Response to COVID-19
  • Marco Polignano, Marco de Gemmis and Giovanni Semeraro.
    Unraveling the Enigma of SPLIT in Large-Language Models: The Unforeseen Impact of System Prompts on LLMs with Dissociative Identity Disorder
  • Leonardo Ranaldi, Giulia Pucci and Fabio Massimo Zanzotto.
    When the order Matters: Analysis of the Role of Sequence Composition on Language Model Pre-Training
  • Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti and Fabio Massimo Zanzotto.
    When Italian is not enough: The limits of the language in multilingual reasoning
  • Aria Rastegar and Pegah Ramezani.
    From ‘It’s All Greek to Me’ to ‘Nur Bahnhof verstehen’: An Investigation of mBERT’s Cross-Linguistic Capabilities
  • Arianna Redaelli and Rachele Sprugnoli.
    Is Sentence Splitting a Solved Task? Experiments to the Intersection Between NLP and Italian Linguistics
  • Giulia Rizzi, Paolo Rosso and Elisabetta Fersini.
    From Explanation to Detection: Multimodal Insights into Disagreement in Misogynous Memes
  • Daniel Russo, Oscar Araque and Marco Guerini.
    To Click it or not to Click it: An Italian Dataset for Neutralising Clickbait Headlines
  • Marco Russodivito, Vittorio Ganfi, Giuliana Fiorentino and Rocco Oliveto.
    AI vs. Human: Effectiveness of LLMs in Simplifying Italian Administrative Documents
  • Elena Sofia Ruzzetti, Federico Ranaldi, Dario Onorati, Davide Venditti, Leonardo Ranaldi, Tommaso Caselli and Fabio Massimo Zanzotto.
    Assessing the Asymmetric Behaviour of Italian Large Language Models across Different Syntactic Structures
  • Martina Saccomando, Andrea Zaninello and Francesca Masini.
    Morphological vs. Lexical Antonyms in Italian: a Computational Study on Lexical Competition
  • Marco Saioni and Cristina Giannone.
    Multimodal Attention is all you need
  • Manuela Sanguinetti, Alessandro Pani, Alessandra Perniciano, Luca Zedda, Andrea Loddo and Maurizio Atzori.
    Assessing Italian Large Language Models on Energy Feedback Generation: A Human Evaluation Study
  • Gabriele Sarti, Tommaso Caselli, Malvina Nissim and Arianna Bisazza.
    Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses
  • Antonio Scaiella, Stefano Costanzo, Elisa Passone, Danilo Croce and Giorgio Gambosi.
    Leveraging Large Language Models for Fact Verification in Italian
  • Daniel Scalena, Elisabetta Fersini and Malvina Nissim.
    A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
  • Wolfgang S. Schmeisser-Nieto, Giacomo Ricci, Simona Frenda, Mariona Taule and Cristina Bosco.
    Implicit Stereotypes: A Corpus-Based Study for Italian
  • Luca Simonetti, Elisabetta Jezek and Guido Vetere.
    Subcategorization of Italian Verbs with LLMs and T-PAS
  • Irene Siragusa and Roberto Pirrone.
    Open Unipa-GPT: an alternative to ChatGPT for Italian chatbot
  • Rachele Sprugnoli and Arianna Redaelli.
    Annotation and Detection of Emotion Polarity in “I Promessi Sposi”: Dataset and Experiments
  • Fabio Tamburini.
    Complexifying BERT using LoRA Adapters
  • Vittoria Tonini, Simona Frenda, Marco Antonio Stranisci and Viviana Patti.
    How do we counter hate speech in Italy?
  • Olga Uryupina.
    Life and Death of Fakes: on Data Persistence for Manipulative Social Media Content
  • Olga Uryupina.
    Multimodal Online Manipulation: Empirical Analysis of Fact-Checking Reports
  • Giovanni Valer, Nicolò Penzo and Jacopo Staiano.
    Nesciun Lengaz Lascià Endò: Machine Translation for Fassa Ladin
  • Marco Vassallo, Giuliano Gabrieli, Valerio Basile and Cristina Bosco.
    Neutral Score Detection in Lexicon-based Sentiment Analysis: the Quartile-based Approach
  • Alessandro Vietti, Domenico De Cristofaro and Picciau Sara.
    Sensitivity of Syllable-Based ASR Predictions to Token Frequency and Lexical Stress
  • Vincenzo Norman Vitale, Loredana Schettino and Francesco Cutugno.
    Modelling filled particles and prolongation using end-to-end Automatic Speech Recognition systems: a quantitative and qualitative analysis.
  • Andrew Zamai, Leonardo Rigutini, Marco Maggini and Andrea Zugarini.
    SLIMER-IT: Zero-Shot NER on Italian Language
  • Kamyar Zeinalipour, Achille Fusco, Asya Zanollo, Marco Maggini and Marco Gori.
    Harnessing LLMs for Educational Content-Driven Italian Crossword Generation
  • Shibingfeng Zhang, Gloria Gagliardi and Fabio Tamburini.
    Voice Activity Detection on Italian Language

Research communications

  • Muhammad Saad Amin, Luca Anselma and Alessandro Mazzei.
    Exploring Data Augmentation in Neural DRS-to-Text Generation
  • Andrei Stefan Bejgu, Edoardo Barba, Luigi Procopio, Alberte Fernández-Castro and Roberto Navigli.
    Word Sense Linking: Disambiguating Outside the Sandbox
  • Helena Bonaldi, Yi-Ling Chung, Gavin Abercrombie and Marco Guerini.
    NLP for Counterspeech against Hate: A Survey and How-To Guide
  • Silvia Casola, Simona Frenda, Soda Marem Lo, Erhan Sezerer, Antonio Uva, Valerio Basile, Cristina Bosco, Alessandro Pedrani, Chiara Rubagotti, Viviana Patti and Davide Bernardi.
    MultiPICo: Multilingual Perspectivist Irony Corpus
  • Pierluigi Cassotti, Stefano De Pascale and Nina Tahmasebi.
    Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types
  • Elisa Di Nuovo, Manuela Sanguinetti, Pier Felice Balestrucci, Cristian Bernareggi, Luca Anselma and Alessandro Mazzei.
    Educational Dialogue Systems for Visually Impaired Students: Introducing a Task-Oriented User-Agent Corpus
  • Giuliano Martinelli, Edoardo Barba and Roberto Navigli.
    Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends
  • Daniela Occhipinti, Michele Marchi, Irene Mondella, Huiyuan Lai, Felice Dell’Orletta, Malvina Nissim and Marco Guerini.
    Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
  • Liviu P. Dinu, Ana Sabina Uban, Alina Maria Cristea, Anca Dinu, Ioan-Bogdan Iordache, Simona Georgescu and Laurentiu Zoicas.
    RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification
  • Stefano Perrella, Lorenzo Proietti, Alessandro Scirè, Edoardo Barba and Roberto Navigli.
    Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!
  • Giulia Rambelli, Emmanuele Chersoni, Claudia Collacciani and marianna bolognesi.
    Can Large Language Models Interpret Noun-Noun Compounds? A Linguistically-Motivated Study on Lexicalized and Novel Compounds
  • Alan Ramponi.
    Language Varieties of Italy: Technology Challenges and Opportunities
  • Leonardo Ranaldi and Giulia Pucci.
    Reasoning Beyond English in Large Language Models
  • Giulia Rizzi, Francesca Gasparini, Aurora Saibene, Paolo Rosso and Elisabetta Fersini.
    Recognizing Misogynous Memes: Biased Models and Tricky Archetypes
  • Daniel Russo, Shane Kaszefski-Yaschuk, Jacopo Staiano and Marco Guerini.
    Countering Misinformation via Emotional Response Generation
  • Gabriele Sarti, Grzegorz Chrupała, Malvina Nissim and Arianna Bisazza.
    Quantifying the Plausibility of Context Reliance in Neural Machine Translation
  • Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar van der Wal, Malvina Nissim and Arianna Bisazza.
    Inseq: An Interpretability Toolkit for Sequence Generation Models
  • Beatrice Savoldi, Andrea Piergentili, Dennis Fucci, Matteo Negri and Luisa Bentivogli.
    Guys or Folks? Toward Gender-Neutral Machine Translation
  • Alessandro Scirè, Karim Ghonim and Roberto Navigli.
    FENICE: Factuality Evaluation of summarization based on Natural Language Inference and Claim Extraction