Neural Machine Translation in the Field of Law. Analysis and Evaluation against Human Reference of NMT Raw Outputs of an Atto Costitutivo of S.r.l. from Italian into German.

Artificial Intelligence (AI) is gaining ever more ground in every sphere of human life, to the point that it is now even used to pass sentences in courts. The use of AI in the field of Law is however deemed quite controversial, as it could provide more objectivity yet entail an abuse of power as well, given that bias in algorithms behind AI may cause lack of accuracy. As a product of AI, machine translation is being increasingly used in the field of Law too in order to translate laws, judgements, contracts, etc. between different languages and different legal systems. In the legal setting of Company Law, accuracy of the content and suitability of terminology play a crucial role within a translation task, as any addition or omission of content or mistranslation of terms could entail legal consequences for companies. The purpose of the present study is to first assess which neural machine translation system between DeepL and ModernMT produces a more suitable translation from Italian into German of the atto costitutivo of an Italian s.r.l. in terms of accuracy of the content and correctness of terminology, and then to assess which translation proves to be closer to a human reference translation. In order to achieve the above-mentioned aims, two human and automatic evaluations are carried out based on the MQM taxonomy and the BLEU metric. Results of both evaluations show an overall better performance delivered by ModernMT in terms of content accuracy, suitability of terminology, and closeness to a human translation. As emerged from the MQM-based evaluation, its accuracy and terminology errors account for just 8.43% (as opposed to DeepL’s 9.22%), while it obtains an overall BLEU score of 29.14 (against DeepL’s 27.02). The overall performances however show that machines still face barriers in overcoming semantic complexity, tackling polysemy, and choosing domain-specific terminology, which suggests that the discrepancy with human translation may still be remarkable.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Evaluation of green algae deployment for organic pollutant removal in urban wastewater through ERE-CALUX potency assessment

The interest of the scientific community towards organic pollutants in freshwater streams is fairly recent. During the past 50 years, thousands of chemicals have been synthesized and released into the general environment. Nowadays their occurrence and effects on several organism, invertebrates, fish, birds, reptiles and also humans are well documented. Because of their action, some of these chemicals have been defined as Endocrine Disrupters Compounds (EDCs) and the public health implications of these EDCs have been the subject of scientific debate. Most interestingly, among those that were noticed to have some influence and effects on the endocrine system were the estrone, the 17β-estradiol, the 17α-estradiol, the estriol, the 17α-ethinylestradiol, the testosterone and the progesterone. This project focused its attention on the 17β-estradiol. Estradiol, or more precisely, 17β-estradiol (also commonly referred to as E2) is a human sex hormone. It belongs to the class of steroid hormones. In spite of the effort to remove these substances from the effluents, the actual wastewater treatment plants are not able to degrade or inactivate these organic compounds that are continually poured in the ecosystem. Through this work a new system for the wastewater treatment was tested, to assess the decrease of the estradiol in the water. It involved the action of Chlorella vulgaris, a fresh water green microalga belonging to the family of the Chlorellaceae. This microorganism was selected for its adaptability and for its photosynthetic efficiency. To detect the decrease of the target compound in the water a CALUX bioassay analysis was chosen. Three different experiments were carried on to pursue the aim of the project. By analysing their results several aspects emerged. It was assessed the presence of EDCs inside the water used to prepare the culture media. C. vulgaris, under controlled conditions, could be efficient for this purpose, although further researches are essential to deepen the knowledge of this complex phenomenon. Ultimately by assessing the toxicity of the effluent against C. vulgaris, it was clear that at determined concentrations, it could affect the normal growth rate of this microorganism.