CEUR Proceedings are online!
https://ceur-ws.org/Vol-3877/
DAY 1: Tuesday, November 26th, 2024
Room D0.02
16:00-16:15 CET
16:00-16:15 – Opening DAY 1: Welcome to NL4AI 2024!
16:15-17:30 CET
16:15-16:30 – Introduction: Roberto Basili (University of Rome, Tor Vergata) and Bernando Magnini (Fondazione Bruno Kessler)
16:30-17:30 – Invited talk: Brando Benifei (Member of the European Parliament) –
“The European AI Act: Challenges and opportunities for ethical and responsible artificial intelligence“
Abstract: The Artificial Intelligence Act, which came into force on 1 August 2024, represents the world’s first comprehensive regulatory framework on artificial intelligence. This talk examines the main provisions of the AI Act, analysing its risk-based approach and the implications for developers, vendors and users of AI systems. Implementation challenges will be discussed, with a focus on requirements for high-risk systems and prohibited practices. The opportunities the AI Act offers to promote responsible innovation, increase consumer trust and establish global standards for ethical AI will also be explored. Finally, the potential impact of the AI Act beyond EU borders and its role in shaping the future of AI governance internationally will be reflected upon.
17:30-18:00 CET
SESSION 1: Generative & Conversational AI
Chair: Lucia Siciliani
17:30-17:45 – Lucrezia Laraspata, Fabio Cardilli, Giovanna Castellano and Gennaro Vessio.
Enhancing human capital management through GPT-driven questionnaire generation [paper]
17:45-18:00 – Diego Gosmar, Deborah A. Dahl, Emmett Coin and David Attwater.
AI Multi-Agent Interoperability Extension for Managing Multiparty Conversations [paper]
DAY 2: Wednesday, November 27th, 2024
Room D0.02
10:30-11:30 CET
10:30-11:30 – Invited talk: Valerio Basile (University of Torino) –
“Modeling and Evaluation for Perspectivist NLP“
Abstract: A recent line of research in NLP proposes to never aggregate human annotations [1], but rather to leverage the worth of knowledge found in label variation for building models [2] and evaluating them [3]. This approach is particularly relevant when dealing with highly subjective aspects of natural language such as irony or undesirable language.
In this talk, I will present the perspectivist paradigm in NLP, and the results of recent and ongoing research focusing on building perspective-aware predictive models and automatically extract human perspectives from annotated data. Particular emphasis will be given to language resources, for training or few-shotting models, but also for benchmarking in the perspectivist framework.
11:30-12:30 CET
SESSION 2: LLM Applications
Chair: Giovanni Bonetta
11:30-11:40 – Patrick Styll, Wojciech Kusa and Allan Hanbury.
Enhancing Clinical Data Capture: Developing a Natural Language Processing Pipeline for Converting Free Text Admission Notes to Structured EHR Data [paper]
11:40-11:50 – Flavio Valerio, Pierpaolo Basile and Marco de Gemmis.
Adapting a Large Language Model to the Legal Domain: A Case Study in Italian [paper]
11:50-12:00 – Loris Di Quilio and Fabio Fioravanti.
A Comprehensive Framework for Aspect-Category Sentiment Analysis [paper]
12:00-12:10 – Irene Siragusa and Roberto Pirrone.
UniQA: an Italian and English Question-Answering Data Set Based on Educational Documents [paper]
12:10-12:20 – Sofia Brenna and Bernardo Magnini.
Last Utterance Proactivity Prediction in Task-oriented Dialogues [paper]
12:20-12:30 – Valeria Nardoni, Marco Lippi, Giulia Hyeraci, Martina Maccari, Amirreza Dehghan Tarazjani, Gianni Virgili, Rosa Gini and Simone Marinai.
Towards Automatically Filling Questionnaires from Clinical Records with Large Language Models [paper]
12:30-13:30 CET
12:30-13:30 – Lunch Break
13:30-15:30 CET
13:30-15:30 – Main Conference: Awards and Industry
16:00-17:15 CET
SESSION 3: Multimodal and NLP Applications
Chair: Marco A. Stranisci
16:00-16:15 – Andrea Seveso, Fabio Mercorio, Mario Mezzanzanica, Daniele Potertì and Antonio Serino.
Disce aut Deficere: Evaluating LLMs Proficiency on the INVALSI Italian Benchmark [dissemination paper]
16:15-16:30 – Antonio Scaiella, Daniele Margiotta, Claudiu Daniel Hromei, Danilo Croce and Roberto Basili.
Evaluating Multimodal Large Language Models for Visual Question-Answering in Italian [paper]
16:30-16:45 – Michele Papucci, Alessio Miaschi and Felice Dell’Orletta.
Fantastic Labels and Where to Find Them: Attention-Based Label Selection for Text-to-Text Classification [paper]
16:45-17:00 – Marta Sartor, Felice Dell’Orletta and Giulia Venturi.
Coherence Evaluation in Italian Language Models [paper]
17:00-17:15 – Calogero Jerik Scozzaro, Matteo Delsanto, Antonio Mastropaolo, Enrico Mensa, Luisa Revelli and Daniele P. Radicioni.
On the Reform of the Italian Constitution: an Interdisciplinary Text Readability Analysis [paper]
17:15-18:00 CET
SESSION 4: Selected Papers
Chair: Claudiu D. Hromei
17:15-17:30 – Elio Musacchio, Lucia Siciliani, Pierpaolo Basile and Giovanni Semeraro.
LLaVA-NDiNO: Empowering LLMs with Multimodality for the Italian Language [paper]
17:30-17:45 – Emanuele Colonna, Alessandro Arezzo, Domenico Roberto, David Landi, Felice Vitulano, Gennaro Vessio and Giovanna Castellano.
Towards Italian Sign Language generation for digital humans [paper]
17:45-18:00 – Closing remarks