Statistical analysis of written languages

La tesi presenta una serie di risultati dell'analisi quantitativa sulla linguistica. Inizialmente sono studiate due fra le leggi empiriche più famose di questo campo, le leggi di Zipf e Heaps, e vengono esposti vari modelli sullo sviluppo del linguaggio. Nella seconda parte si giunge alla discussione di risultati più specifici sulla presenza di fenomeni di burstiness e di correlazioni a lungo raggio nei testi. Tutti questi studi teorici sono affiancati da analisi sperimentali, svolte utilizzando varie traduzioni del libro "Guerra e pace" di Leo Tolstoj e concentrate principalmente sulle eventuali differenze riscontrabili tra le diverse lingue.

The red herring argument in everyday life, and in the film, "American Beauty"

The Red Herring Argument is a logical device found in many areas of life. This thesis will narrow the focus, however, and examine how it is employed in the legal technique called “Chewbacca defense,” and in the film, “American Beauty.”

Quality and Aspect based Argument Generation

Natural Language Processing has always been one of the most popular topics in Artificial Intelligence. Argument-related research in NLP, such as argument detection, argument mining and argument generation, has been popular, especially in recent years. In our daily lives, we use arguments to express ourselves. The quality of arguments heavily impacts the effectiveness of our communications with others. In professional fields, such as legislation and academic areas, arguments of good quality play an even more critical role. Therefore, argument generation with good quality is a challenging research task that is also of great importance in NLP. The aim of this work is to investigate the automatic generation of arguments with good quality, according to the given topic, stance and aspect (control codes). To achieve this goal, a module based on BERT [17] which could judge an argument's quality is constructed. This module is used to assess the quality of the generated arguments. Another module based on GPT-2 [19] is implemented to generate arguments. Stances and aspects are also used as guidance when generating arguments. After combining all these models and techniques, the ranks of the generated arguments could be acquired to evaluate the final performance. This dissertation describes the architecture and experimental setup, analyzes the results of our experimentation, and discusses future directions.