Five papers accepted at CLIC-it 2019

The task of short answer grading is aimed at assessing the outcome of an exam by automatically analysing students’ answers in natural language and deciding whether they should pass or fail the exam. In this paper, we tackle this task training an SVM classifier on real data taken from a University statistics exam, showing that simple concatenated sentence embeddings used as features yield results around 0.90 F1. We also release the dataset, that to our knowledge is the first freely available dataset of this kind in Italian.

In this paper we present a multi-genre corpus spanning 50 years of European history. It contains a comprehensive collection of Alcide De Gasperi’s public documents, 2,762 in total, written or transcribed between 1901 and 1954. The corpus comprises different types of texts, including newspaper articles, propaganda documents, official letters and parliamentary speeches. The corpus is freely available and includes several annotation layers, i.e. key-concepts, lemmas, PoS tags, person names and geo-referenced places, representing a high-quality ‘silver’ annotation. We believe that this resource can foster research in historical corpus analysis, stylometry and computational social science, among others.

Despite the number of approaches recently proposed in NLP for detecting abusive language on social networks, the issue of developing hate speech detection systems that are robust across different platforms is still an unsolved problem. In this paper we perform a comparative evaluation on datasets for hate speech detection in Italian, extracted from four different social media platforms, i.e. Facebook, Twitter, Instagram and WhatsApp. We show that combining such platform-dependent datasets to take advantage of training data developed for other platforms is beneficial, although their impact varies depending on the social network under consideration.