All systems participating at EVALITA are eligible providing that they satisfy the following conditions: (i) at least one young researcher (Ph.D. or undergraduate student) as a co-author, and (ii) the authors must have open-sourced their software.
Eligible systems are evaluated according to the following criteria:
- Novelty with respect to the state of the art;
- Originality (in terms of identification of new linguistic resources, identification of linguistically motivated features, and implementation of a theoretical framework grounded in linguistics);
- Critical insight, paving the way to future challenges (deep error analysis, discussion on the limits of the proposed system, discussion of the inherent challenges of the task);
- Technical soundness and methodological rigor.
The prize for the best system consists of 500 euros.
List of 2023 awardees:
- EVALITA best system: ExtremITA at EVALITA 2023: Multi-Task Sustainable Scaling to Large Language Models at its Extreme (all tasks): Claudiu D. Hromei, Danilo Croce, Valerio Basile and Roberto Basili
- Special mention: DH-FBK at HODI: Multi-Task Learning with Classifier Ensemble Agreement, Oversampling and Synthetic Data: Elisa Leonardelli and Camilla Casula
- Special mention: IUSS-NeTS at LangLearn: The role of morphosyntactic features in language development assessment: Matilde Barbini, Emma Zanoli and Cristiano Chesi
List of 2020 awardees:
- EVALITA best system: UNITOR@Sardistance2020: Combining Transformer-based architectures and Transfer Learning for robust Stance Detection (HaSpeeDe, IronITA, ABSITA, and GxG Tasks): Simone Giorgioni, Marcello Politi, Samir Salman, Roberto Basili and Danilo Croce
- Special mention: UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations: Gabriele Sarti
- Special mention: rmassidda @ DaDoEval: Document Dating Using Sentence Embeddings at EVALITA 2020: Riccardo Massidda
List of 2018 awardees:
- EVALITA best system: Multi-task learning in Deep Neural Networks (HaSpeeDe, IronITA, ABSITA, and GxG Tasks): Lorenzo De Mattei, Andrea Cimino and Felice Dell’Orletta
- Special mention: Automatic Identification of Misogyny in English and Italian Tweets with a Multilingual Hate (AMI Task): Endang Wahyu Pamungkas, Alessandra Teresa Cignarella, Valerio Basile and Viviana Patti
- Special mention: Bidirectional Attentional LSTM for Aspect Based Sentiment Analysis on Italian (ABSITA Task): Giancarlo Nicola