Program

09.00 - 9.15

Chair: Luisa Bentivogli


Opening

9.15 - 10.00

Chair: Sara Tonelli

Keynote talk: Barbara Plank (LMU Munich)

Are LLMs narrowing our Horizon? Let's embrace variation in NLP!  

(Keynote talk at ACL 2024)

10.00 - 10.45

Chair: Alessio Brutti

Session 1: Language Technologies and Foundation Models

Marco Gaido, Sara Papi, Matteo Negri and Luisa Bentivogli. “Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?”. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Outstanding paper and SAC award at ACL2024)

Marco Gaido*, Sara Papi*, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri. “Towards an Open-Source Speech Foundation Model for EU: 950,000 Hours of Open-Source Compliant Speech Data for EU Languages” (accepted at EMNLP 2024)

Umberto Cappellazzo, Enrico Fini, Muqiao Yang, Daniele Falavigna, Alessio Brutti, Bhiksha Raj. "Continual Contrastive Spoken Language Understanding". Findings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

10.45 - 11.15

Coffee break

11.15 - 12.00

Chair: Mauro Dragoni

Session 2: Trustworthy and Reproducible LT

Camilla Casula, Sebastiano Vecellio Salto, Alan Ramponi, Sara Tonelli “Delving into Qualitative Implications of Synthetic Data for Hate Speech Detection” (accepted at EMNLP 2024)

Helena Bonaldi, Greta Damo, Nicolás Benjamín Ocampo, Elena Cabrio, Serena Villata, Marco Guerini “Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering” (accepted at EMNLP 2024)

Sara Papi*, Marco Gaido*, Andrea Pilzer and Matteo Negri. "When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP". Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)

12.00 - 13.00

Chair: Daniele Falavigna

Building the LT Future: Insights from the LT@FBK research units

Alessio Brutti: Audio-visual speech recognition with LLMs (STEK group) (TBC)

Monica Consolandi: Misunderstanding and Risk Communication in Healthcare (IDA group)

Dennis Fucci: Explainability for speech-to-text generation (MT group)

Marco Rovera: A World through Events: Italian Event Processing in the Making (DH group) 

Daniel Russo Countering Misinformation with LLMs (LAND group)

Andrea Zaninello: Explanations explained. Influence of free-text explanations on LLMs and the role of implicit knowledge. (NLP group)

13.00 - 14.00

Lunch

14.00 - 14.45

Chair: Marco Guerini

Session 3: Human-Centered LT

Alan Ramponi. "Language Varieties of Italy: Technology Challenges and Opportunities". Transactions of the Association for Computational Linguistics, 2024. 

Beatrice Savoldi, Sara Papi, Matteo Negri, Ana Guerberof, Luisa Bentivogli “What the harm: Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study”  (accepted at EMNLP 2024)

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". Findings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

14.45 - 15.30

Chair: Matteo Negri

Session 4: LT Applications and Datasets

Nicolò Penzo, Maryam Sajedinia, Bruno Lepri, Sara Tonelli, Marco Guerini “Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations” (accepted at EMNLP 2024)

Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli. “Streaming Speech-to-Text Speech Translation with Attention-based History Selection”. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Daniela Occhipinti, Serra Tekiroglu, and Marco Guerini. "PRODIGy: a PROfile-based DIalogue Generation dataset". Findings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024).

15.30 - 16.45

Posters + coffee break

Helena Bonaldi, Yi-Ling Chung, Gavin Abercrombie, and Marco Guerini. "NLP for Counterspeech against Hate: A Survey and How-To Guide". Findings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024).

Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti. "Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters". Proceedings of Interspeech 2024.

Camilla Casula, Elisa Leonardelli and Sara Tonelli. "Don’t Augment, Rewrite? Assessing Abusive Language Detection with Synthetic Data". Findings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Saeed Farzi*, Soumitra Ghosh*, Alberto Lavelli and Bernardo Magnini. "Get the Best out of 1B LLMs: Insights from Information Extraction on Clinical Documents". BioNLP Workshop 2024.

Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli. “How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena”. Proceedings of LREC-COLING 2024.

Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri and Luisa Bentivogli. “SBAAM! Eliminating Transcript Dependency in Automatic Subtitling”. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Saba Ghanbari Haez, Marina Segala, Patrizio Bellan, Simone Magnolini, Leonardo Sanna, Monica Consolandi and Mauro Dragoni. "A Retrieval-Augmented Generation Strategy to Enhance Medical Chatbot Reliability"  Proceedings of the International Conference on Artificial Intelligence in Medicine (AIME 2024).

Nicolò Penzo, Antonio Longa, Bruno Lepri, Sara Tonelli, and Marco Guerini. "Putting Context in Context: the Impact of Discussion Structure on Text Classification". Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024).

Alan Ramponi, Camilla Casula and Stefano Menini. "VARIATIONIST: Exploring Multifaceted Variation and Bias in Written Language Data" (demo paper). Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Beatrice Savoldi, Andrea Piergentili, Dennis Fucci, Matteo Negri, Luisa Bentivogli. “A Prompt Response to the Emerging Need of Automatic Gender-Neutral Translation”. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024).

16.45 - 17.00

Closing