Editorial reorganization of an alphabetically ordered collection of short stories: analysis of problems and hypothesis of possible solutions

This paper aims to show, analyze and solve the problems related to the translation of the book with meaning-bond alphabetically ordered chapter titles La vita non è in ordine alfabetico, by the Italian writer Andrea Bajani. The procedure is inevitable for a possible translation of the book, and it is necessary to have a preliminary pattern to follow. After translating the whole book, not only is a revision fundamental, but a restructure and reorganization of the collection may be required, hence, what this thesis offers is a scheme to start from, together with an analysis of the possible problems that may arise, and a useful method to find a solution.

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.