Hierarchical Multi-Label Text Classification in a Low-Resource Setting

In this thesis we address a multi-label hierarchical text classification problem in a low-resource setting and explore different approaches to identify the best one for our case. The goal is to train a model that classifies English school exercises according to a hierarchical taxonomy with few labeled data. The experiments made in this work employ different machine learning models and text representation techniques: CatBoost with tf-idf features, classifiers based on pre-trained models (mBERT, LASER), and SetFit, a framework for few-shot text classification. SetFit proved to be the most promising approach, achieving better performance when during training only a few labeled examples per class are available. However, this thesis does not consider all the hierarchical taxonomy, but only the first two levels: to address classification with the classes at the third level further experiments should be carried out, exploring methods for zero-shot text classification, data augmentation, and strategies to exploit the hierarchical structure of the taxonomy during training.

Analisi del film L'appartamento spagnolo: multilinguismo e comunicazione interculturale

The present research study focuses on intercultural communication and how its dynamics are portrayed in the Italian version of the movie L’appartamento spagnolo (original title: L’auberge espagnol) by Cédric Klapisch. The first chapter introduces the movie in all its main features, such as plot, setting, characters, languages, main themes, and sequels. The second chapter focuses on the dynamics of intercultural communication through the analysis of the most representative scenes of the movie. It is worth noting that the notion of intercultural communication comprises a lot of different kinds of communication, meaning not only communication among people coming from different countries and speaking a different language, but also among different generations, people with different social backgrounds, with a different social status, etc. However, language is indeed crucial to mutual understanding and it plays a fundamental role in communication. For this reason, the third chapter focuses on the multilingual dimension of the movie, since the issue of intercultural communication is also conveyed through a variety of languages. The aim is to analyze the different strategies used in the Italian dubbed version in order to manage the presence of different languages and to examine how such strategies affect the overall consistency of the dialogues and the effect achieved on the audience.