Search

Welcome to EVALITA 2020! EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for Italian. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC, http://www.ai-lc.it) and it is endorsed by the Italian Association for Artificial Intelligence (AIxIA, http://www.aixia.it) and the Italian Association for Speech Sciences (AISV, http://www.aisv.it). This volume includes the reports of both task organisers and participants to all of the...

This paper provides a summary of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA2020) which was held online on December 17th, due to the 2020 COVID-19 pandemic. The 2020 edition of Evalita included 14 different tasks belonging to five research areas, namely: (i) Affect, Hate, and Stance, (ii) Creativity and Style, (iii) New Challenges in Long-standing Tasks, (iv) Semantics and Multimodality, (v) Time and Diachrony. This paper provides a description of the tasks and the key findings from the analysis of participant outcomes. Moreover, it provides a detailed analysis of the participants and task organizers which demonstrates the growing interest with respect to this campaign. Finally, a detailed analysis of the evaluation of tasks across the past seven editions is provided; this allows to assess how the research carried out by the Italian community dealing with Computational Linguistics has evolved in terms of popular tasks and paradigms during the last 13 years.

This paper describes a collection of modules for Italian language processing based on CoreNLP and Universal Dependencies (UD). The software will be freely available for download under the GNU General Public License (GNU GPL). Given the flexibility of the framework, it is easily adaptable to new languages provided with an UD Treebank. Questo lavoro descrive un insieme di strumenti di analisi linguistica per l’Italiano basati su CoreNLP e Universal Dependencies (UD). Il software sarà liberamente scaricabile sotto licenza GNU General Public License (GNU GPL). Data la sua flessibilità, il framework è facilmente adattabile ad altre lingue con una Treebank UD.

Recent psycholinguistic and neuroscientific research has emphasized the crucial role of emotions for abstract words, which would be grounded by affective experience, instead of a sensorimotor one. The hypothesis of affective embodiment has been proposed as an alternative to the idea that abstract words are linguistically coded and that linguistic processing plays a key role in their acquisition and processing. In this paper, we use distributional semantic models to explore the complex interplay between linguistic and affective information in the representation of abstract words. Distributional analyses on Italian norming data show that abstract words have more affective content and tend to co-occur with contexts with higher emotive values, according to affective statistical indices estimated in terms of distributional similarity with a restricted number of seed words strongly associated with a set of basic emotions. Therefore, the strong affective content of abstract words might just be an indirect byproduct of co-occurrence statistics. This is consistent with a version of representational pluralism in which concepts that are fully embodied either at the sensorimotor or at the affective level live side-by-side with concepts only indirectly embodied via their linguistic associations with other embodied words.

In this paper, we illustrate the creation of a NER for the Public Administration (PA) domain. We discuss the creation of an annotated corpus with documents from the Italian Albo Pretorio Nazionale and provide results of the system evaluation. In questo lavoro mostriamo la creazione di un NER per il dominio della Pubblica Amministrazione (PA). Presentiamo la creazione del corpus formato da documenti dell’Albo Pretorio Nazionale e mostriamo i risultati della valutazione del sistema.

This paper studies the relationship between the valence, one of the psycholinguistic variables in the Italian version of ANEW (Montefinese et al., 2014), and emotive scores calculated by exploiting distributional methods (Passaro et al., 2015). We show two methods to infer valence from fine grained emotions and discuss their evaluation. Questo lavoro studia la relazione tra la valenza, una delle variabili psicolinguistiche presenti nella versione italiana di ANEW (Montefinese et al., 2014) e degli score emotivi calcolati distribuzionalmente (Passaro et al., 2015). Mostriamo due metodi per inferire la valenza a partire da tali valori e ne discutiamo la valutazione.

In recent years computational linguistics has seen a rising interest in subjectivity, opinions, feelings and emotions. Even though great attention has been given to polarity recognition, the research in emotion detection has had to rely on small emotion resources. In this paper, we present a methodology to build emotive lexicons by jointly exploiting vector space models and human annotation, and we provide the first results of the evaluation with a crowdsourcing experiment. Negli ultimi anni si è affermato un crescente interesse per soggettività, opinioni e sentimenti. Nonostante sia stato dato molto spazio al riconoscimento della polarità, esistono ancora poche risorse disponibili per il riconoscimento di emozioni. In questo lavoro presentiamo una metodologia per la creazione di un lessico emotivo, sfruttando annotazione manuale e spazi distribuzionali, e forniamo i primi risultati della valutazione effettuata tramite crowdsourcing.

English. We report on three experiments aimed at comparing two popular methods for the automatic extraction of Word Combinations from corpora, with a view to evaluate: i) their efficacy in acquiring data to be included in a combinatory resource for Italian; ii) the impact of different types of benchmarks on the evaluation itself. Italiano. Presentiamo i risultati di tre esperimenti che mirano a confrontare due metodi di estrazione automatica di combinazioni di parole da corpora, con lo scopo di: (i) valutare l’efficacia dei due metodi per acquisire dati da includere in una risorsa combinatoria per l’italiano, e (ii) analizzare e confrontare i metodi di valutazione stessi.

SUMMARY. This paper describes the CoLing Lab system for the EVALITA 2014 SENTIment POLarity Classification SENTIPOLC) task. Our system is based on a SVM classifier trained on the rich set of lexical, global and twitter-specific features described in these pages. Over all, our system reached a 0.63 weighted F-score on the test set provided by the task organizers. RIASSUNTO. Questo contributo descrive il sistema CoLing Lab sviluppato per il task di SENTIment POLarity Classification (SENTIPOL C) organizzato nel contesto della campagna EVALITA 2014. Il nostro sistema e basato su un classificatore SVM addestrato sulle feature lessicali, globali e specifiche del canale twitter descritte in queste pagine. Il nostro sistema raggiunge uno score di circa 0.63 nel test set fornito dagli organizzatori del task.