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.

Deposizione elettrochimica di esacianoferrato di rame tramite un metodo "a due step"; caratterizzazione e valutazione delle prestazioni

In this thesis we have identified two electrochemical procedures for preparing two compounds of copper hexacyanoferrate (CuHCF) films with different compositions and structures. The deposition were carried out using a “two steps” method consisting in electrochemical oxidation of previously deposited metallic copper on carbon substrates (glassy carbon and graphite foil electrodes) in K3[Fe(CN)6] solution. Both films, CuHCF-methodA and CuHCF-methodB, were characterized by cyclic voltammetry (GC) and their study using XANES spectroscopy revealed evidence of different structures. Additionally, insertion and extraction of different cations (Na+, K+, Mg2+, Al3+ and Cs+) were performed and the results indicate that CuHCF-methodA has slightly better performances and operational stability than CuHCF-methodB. Data from galvanostatic charge-discharge tests confirme the latter observation. An application for amperometric detection of H2O2 and SEM micrographs are also reported for both films (method A and B). Comparing these results with a previous work of our research group, seems that the deposition of two different compounds using methodA and methodB is due to the different stoichiometry of ions Cu2+ e [Fe(CN)6]3– created near electrode surface during the dissolution step.