Andrea Galassi

The system guarantees auditability, explainability, and preserves the privacy of the user. We implemented and validated our proposal on a small case study concerning applicants from Nigeria, but in the future we will extend it to further cases.

Our Natural Language module relies on neural representations and LLM to associate the user request with the concepts mapped in the knowledge base. The Argumentative Reasoning module computes the answer or asks for further information if necessary.

Our work "A Chatbot for Asylum-Seeking Migrants in Europe" has been accepted for publication at IEEE ICTAI, where @BettinaFazzinga will present it! Preprint: doi.org/10.48550/arXiv… This work was supported by @humaneainet as a micro-project #chatbot #migration #argumentation

@MichelaMilano1 giving a speech about the future of #AI at Future Artificial Intelligence Research General Conference in Naples #FAIR

Today we are presenting our works "Promoting Fairness and Diversity in Speech Datasets for Mental Health and Neurological Disorders Research" and "ACME: A Chatbot for Migrants in Europe" during the welcome reception of @hhai_conference @humaneainet

1/5 🚀 Thrilled to announce our latest paper, "Promoting Fairness and Diversity in Speech Datasets for Mental Health and Neurological Disorders Research" is here! 🗒️ Read more about our findings: arxiv.org/abs/2406.04116… #AI #MachineLearning #MentalHealth #Speech

A Corpus for Sentence-Level Subjectivity Detection on English News Articles aclanthology.org/2024.lrec-main… Poster 807 on May 23, 15:30 - 17:10, Room: Poster Area II (Pavillion 1 - Lingotto Fiere)

PejorativITy: Disambiguating Pejorative Epithets to Improve Misogyny Detection in Italian Tweets aclanthology.org/2024.lrec-main… Presentation on May 22, 12:20 - 12:40, Room: Berlino

Check out our works at @LrecColing resulting from our collaboration with @_albarron_'s group: On 22: PejorativITy: Disambiguating Pejorative Epithets to Improve Misogyny Detection in Italian Tweets On 23: A Corpus for Sentence-Level Subjectivity Detection on English News Articles

🚀 Introducing the #Minerva Models! The first family of #LLMs trained from scratch on #Italian (& #English). @fondazione_fair @Cineca1969 👉nlp.uniroma1.it/minerva 350M, 1B, 3B base models 🔔Stay tuned for more updates! #NLProc #MachineLearning #AI #GenerativeNLP #GenerativeAI

As part of the work, we release a novel corpus of 50 Terms of Service documents in 4 languages, for a total of 200 documents, where clauses have been annotated according to the type and severity of unfairness. 5/5

We found that relying on machine translation at prediction time seems to be the best solution, but only in case the quality of the translation system is adequate. Projecting annotations or translating training documents is also a reasonable option. 4/5

Our last work, "Unfair clause detection in terms of service across multiple languages", is now available on the website of the Artificial Intelligence and Law journal @frannyezooey @GiovanniSartor3 doi.org/10.1007/s10506… 🧵👇1/5

The #CLEF2024 #CheckThat!Lab2024 on Checkworthiness, Subjectivity, Persuasion, Roles, Authorities and Adversarial Robustness Multiple lang: Arabic, Bulgarian, English, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English T1: Check-worthiness estimation T2: Subjectivity T3: Persuasion Techniques T4: Detecting hero, villain, and victim from memes T5: Rumor Verification using Evidence from Authorities T6: Robustness of Credibility Assessment with Adversarial Examples More: checkthat.gitlab.io Data/Code: shorturl.at/agtAJ Reg: shorturl.at/ikAMX W/ @clef_initiative, @_albarron_, @preslav_nakov, @giodsm, @tamer_elsayed, @wzaghouani, @MaramHasanain, @Chengkai_Li, @rubenmiguez, Julia Maria Struß, Gautam Kishore Shahi, @mucahidkutlu, @aGalaxy42, Federico Ruggeri, ​​@robikuetcse, @FHaouari @Tanmoy_Chak #checkthatlab2024 #CLEF2024

Excited to present our work “Multimodal Fallacy Classification in Political Debates” at EACL 2024 in Malta today! 🇲🇹Check out the paper here: aclanthology.org/2024.eacl-shor… #EACL2024 #Multimodal #FallacyClassification #PoliticalDebates 1/3

#NLProc, this year #CLEF2024 #CheckThat!Lab2024 offers tasks on Checkworthiness, Subjectivity, Persuasion, Roles, Authorities and Adversarial Robustness Multiple lang: Arabic, Bulgarian, English, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English Please register and participate. More: checkthat.gitlab.io Data/Code: shorturl.at/agtAJ Reg: shorturl.at/ikAMX W/ @clef_initiative, @_albarron_, @preslav_nakov, @giodsm, @tamer_elsayed, @wzaghouani, @MaramHasanain, @Chengkai_Li, @rubenmiguez, Julia Maria Struß, @mucahidkutlu, @aGalaxy42, Federico Ruggeri, ​​@robikuetcse, @FHaouari @Tanmoy_Chak #checkthatlab2024 #CLEF2024

The #CLEF2024 #CheckThat!Lab2024 on Checkworthiness, Subjectivity, Persuasion, Roles, Authorities and Adversarial Robustness Multiple lang: Arabic, Bulgarian, English, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English T1: Check-worthiness estimation T2: Subjectivity T3: Persuasion Techniques T4: Detecting hero, villain, and victim from memes T5: Rumor Verification using Evidence from Authorities T6: Robustness of Credibility Assessment with Adversarial Examples More: checkthat.gitlab.io Data/Code: shorturl.at/agtAJ Reg: shorturl.at/ikAMX W/ @clef_initiative, @_albarron_, @preslav_nakov, @giodsm, @tamer_elsayed, @wzaghouani, @MaramHasanain, @Chengkai_Li, @rubenmiguez, Julia Maria Struß, Gautam Kishore Shahi, @mucahidkutlu, @aGalaxy42, Federico Ruggeri, ​​@robikuetcse, @FHaouari @Tanmoy_Chak #checkthatlab2024 #CLEF2024