EVALITA 2023
Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian

Table of Contents

• Preface
  Summary: There were 51 papers submitted for peer-review, 51 papers were accepted for this volume, 31 as regular papers and 20 as short papers.
• EVALITA 2023: Overview of the 8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian
  Mirko Lai, Stefano Menini, Marco Polignano, Valentina Russo, Rachele Sprugnoli, Giulia Venturi

Keynote Talk

• Challenges for NLP shared tasks in the chatGPT era
  Julio Gonzalo

Multi-Track System

• ExtremITA at EVALITA 2023: Multi-Task Sustainable Scaling to Large Language Models at its Extreme
  Claudiu D. Hromei, Danilo Croce, Valerio Basile, Roberto Basili
• O-Dang at HODI and HaSpeeDe3: A Knowledge-Enhanced Approach to Homotransphobia and Hate Speech Detection in Italian
  Chiara Di Bonaventura, Arianna Muti, Marco Antonio Stranisci

Track "Affect"

EMit – Categorical Emotion Detection in Italian Social Media

• EMit at EVALITA 2023: Overview of the Categorical Emotion Detection in Italian Social Media Task
  Oscar Araque, Simona Frenda, Rachele Sprugnoli, Debora Nozza, Viviana Patti
• Emotion Hunters at EMit: Categorical Emotion Detection combining BERT and ChatGPT models (short paper)
  Gianluca Calo', Francesco Massafra, Berardina De Carolis, Corrado Loglisci
• App2Check at EMit: Large Language Models for Multilabel Emotion Classification (short paper)
  Gioele Cageggi, Emanuele Di Rosa, Asia Uboldi
• ABCD team at EMit: Ensemble Approach for Categorial Emotion Detection in Social Media Messages (short paper)
  Nguyen Ba Dai, Nguyen Ngoc Phuong Uyen, Dang Van Thin

EmotivITA – Dimensional and Multi-dimensional emotion analysis

• EmotivITA at EVALITA2023: Overview of the Dimensional and Multidimensional Emotion Analysis Task
  Giovanni Gafà, Francesco Cutugno, Marco Venuti
• ISTC-CNR at EmotivITA: Towards Better Dimensional and multi-dimensional Analysis of VAD Emotions (short paper)
  Luana Bulla, Misael Mongiovì

Track "Authorship Analysis"

PoliticIT – Political Ideology Detection in Italian Texts

• PoliticIT at EVALITA 2023: Overview of the Political Ideology Detection in Italian Texts Task
  Daniel Russo, Salud María Jiménez-Zafra, José Antonio García-Díaz, Tommaso Caselli, L. Alfonso Ureña-López, Rafael Valencia-García
• INFOTEC-LaBD at PoliticIT: Political Ideology Detection in Italian Texts
  Hiram Cabrera-Pineda, Eric Sadit Téllez, Sabino Miranda
• UMUTeam at PoliticIT-EVALITA2023: Evaluating Transformer Model for Detecting Political Ideology in Italian Texts (short paper)
  Ronghao Pan, Ángela Almela, Francisco García-Sánchez
• Tübingen at PoliticIT: Exploring SVMs, Pretrained Language Models, and Linguistic Transfer for Ideology Detection in Social Media
  Çağrı Çöltekin, Matteo Brivio, Fidan Can
• URJC-Team at PoliticIT: Political Ideology Detection in Italian Texts Using Transformers Architectures (short paper)
  Miguel Ángel Rodríguez-García

GeoLingIt – Geolocation of Linguistic Variation in Italy

• GeoLingIt at EVALITA 2023: Overview of the Geolocation of Linguistic Variation in Italy Task
  Alan Ramponi, Camilla Casula
• DANTE at GeoLingIt: Dialect-Aware Multi-Granularity Pre-training for Locating Tweets within Italy
  Giuseppe Gallipoli, Moreno La Quatra, Daniele Rege Cambrin, Salvatore Greco, Luca Cagliero
• Galliz at GeoLingIt: Enhancing BERT with Vocabulary Knowledge for Predicting the Region of Language Varieties of Italy
  Tiziano Labruna, Simone Gallo
• ba𝜌tti at GeoLingIt: Beyond Boundaries, Enhancing Geolocation Prediction and Dialect Classification on Social Media in Italy
  Alkis Koudounas, Flavio Giobergia, Irene Benedetto, Simone Monaco, Luca Cagliero, Daniele Apiletti, Elena Baralis
• Salogni at GeoLingIt: Geolocalization by Fine-tuning BERT (short paper)
  Ilaria Salogni

LangLearn – Language Learning Development

• LangLearn at EVALITA 2023: Overview of the Language Learning Development Task
  Chiara Alzetta, Dominique Brunato, Dell’Orletta, Alessio Miaschi, Kenji Sagae, Claudia H. Sánchez-Gutiérrez, Giulia Venturi
• BERT_4EVER at LangLearn: Language Development Assessment Model based on Sequential Information Attention Mechanism
  Hongyan Wu, Nankai Lin, Shengyi Jiang, Lixian Xiao
• IUSS-NeTS at LangLearn: The role of morphosyntactic features in language development assessment
  Matilde Barbini, Emma Zanoli, Cristiano Chesi
• bot.zen at LangLearn: regressing towards interpretability (short paper)
  Egon W. Stemle, Martina Tebaldini, Francesca Bonanni, Filippo Pellegrino, Paolo Brasolin, Greta H. Franzini, Jennifer-Carmen Frey, Olga Lopopolo, Stefania Spina

Track "Computational Ethics"

HaSpeeDe 3 – Political and Religious Hate Speech Detection

• HaSpeeDe3 at EVALITA 2023: Overview of the Political and Religious Hate Speech Detection task
  Mirko Lai, Fabio Celli, Alan Ramponi, Sara Tonelli, Cristina Bosco, Viviana Patti
• CHILab at HaSpeeDe3: Overview of the Taks A Textual (short paper)
  Irene Siragusa, Roberto Pirrone
• LMU at HaSpeeDe3: Multi-Dataset Training for Cross-Domain Hate Speech Detection
  Viktor Hangya, Alexander Fraser
• BERTicelli at HaSpeeDe 3: Fine-tuning and Cross-validating Large Language Models for Hate Speech Detection
  Leonardo Grotti, Patrick Quick

HODI – Homotransphobia Detection in Italian

• HODI at EVALITA 2023: Overview of the first Shared Task on Homotransphobia Detection in Italian
  Debora Nozza, Alessandra Teresa Cignarella, Greta Damo, Tommaso Caselli, Viviana Patti
• CHILab at HODI: A minimalist approach (short paper)
  Irene Siragusa, Roberto Pirrone
• Team_Tamil at HODI: Few-Shot Learning for Detecting Homotransphobia in Italian Language
  Rahul Ponnusamy, Prasanna Kumar Kumaresan, Kishore Kumar Ponnusamy, Charmathi Rajkumar, Ruba Priyadharshini, Bharathi Raja Chakravarthi
• LCTs at HODI: Homotransphobic Speech Detection on Italian Tweets (short paper)
  Davide Locatelli, Lorenzo Locatelli
• DH-FBK at HODI: Multi-Task Learning with Classifier Ensemble Agreement, Oversampling and Synthetic Data
  Elisa Leonardelli, Camilla Casula

MULTI-Fake-DetectiVE – MULTImodal Fake News Detection and Verification

• MULTI-Fake-DetectiVE at EVALITA 2023: Overview of the MULTImodal Fake News Detection and VErification Task
  Alessandro Bondielli, Pietro Dell’Oglio, Alessandro Lenci, Francesco Marcelloni, Lucia C. Passaro, Marco Sabbatini
• HIJLI-JU-CLEF at MULTI-Fake-DetectiVE: Multimodal Fake News Detection Using Deep Learning Approach (short paper)
  Sandip Sarkar, Nripen Tudu, Dipankar Das
• AIMH at MULTI-Fake-DetectIVE: System Report (short paper)
  Giovanni Puccetti, Andrea Esuli
• PoliTo at MULTI-Fake-DetectiVE: Improving FND-CLIP for Multimodal Italian Fake News Detection
  Lorenzo D’Amico, Davide Napolitano, Lorenzo Vaiani, Luca Cagliero

ACTI – Automatic Conspiracy Theory Identification

• ACTI at EVALITA 2023: Automatic Conspiracy Theory Identification Task Overview (short paper)
  Giuseppe Russo, Niklas Stoehr, Manoel Horta Ribeiro
• Vitali at ACTI – Transformer-based Conspiracy Theory Identification
  Michael Vitali, Vincenzo Scotti, Mark James Carman
• UPB at ACTI: Detecting Conspiracies using fine tuned Sentence Transformers (short paper)
  Andrei Paraschiv, Mihai Dascalu
• sCambiaMenti at ACTI: Ensemble model with majority voting for Automatic Conspiracy Detection (short paper)
  Selene Bianco, Daniela Salusso
• Cicognini at ACTI: Analysis of techniques for conspiracies individuation in Italian (short paper)
  Giacomo Cignoni, Alessandro Bucci
• Giobergia at Multi-Task Transformer Tuning for Joint Conspiracy Theory Detection and Classification
  Flavio Giobergia

Track "New Challenges in Long-standing Tasks"

NERMuD – Named-Entities Recognition on Multi-Domain Documents

• NERMuD at EVALITA 2023: Overview of the Named-Entities Recognition on Multi-Domain Documents Task (short paper)
  Alessio Palmero Aprosio, Teresa Paccosi

CLinkaRT – Linking a Lab Result to its Test Event in the Clinical Domain

• CLinkaRT at EVALITA 2023: Overview of the Task on Linking a Lab Result to its Test Event in the Clinical Domain
  Begoña Altuna, Goutham Karunakaran, Alberto Lavelli, Bernardo Magnini, Manuela Speranza, Roberto Zanoli
• Simple Ideas at CLinkaRT: LeaNER and MeaNER Relation Extraction
  Marius Micluța-Câmpeanu, Liviu P. Dinu
• Polimi at CLinkaRT: a Conditional Random Field vs a BERT-based approach
  Vittorio Torri, Francesca Ieva

WIC-ita – Word-in-Context task for Italian

• WiC-ITA at EVALITA2023: Overview of the EVALITA2023 Word-in-Context for ITAlian Task
  Pierluigi Cassotti, Lucia Siciliani, Lucia C. Passaro, Maristella Gatto, Pierpaolo Basile
• The Time-Embedding Travelers at WiC-ITA
  Francesco Periti, Haim Dubossarsky
• LG at WiC-ITA: Exploring the relation between semantic distance and equivalence in translation. (short paper)
  Lorenzo Gregori

DisCoTEX – Assessing DIScourse COherence in Italian TEXts

• DisCoTex at EVALITA 2023: Overview of the Assessing DIScourse COherence in Italian TEXts task
  Dominique Brunato, Davide Colla, Felice Dell’Orletta, Irene Dini, Daniele Paolo Radicioni, Andrea Amelio Ravelli
• IUSSNets at DisCoTeX: A fine-tuned approach to coherence
  Emma Zanoli, Matilde Barbini, Cristiano Chesi
• MPG at DisCoTeX: Predicting Text Coherence by Tree-based Modelling of Linguistic Features (short paper)
  Martina Galletti, Pietro Gravino, Giulio Prevedello