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.

Assessing the effectiveness of ISO 3382 for evaluating the acoustical quality of italian historical theatres: the case study of the Bonci Theatre

The present study concerns the acoustical characterisation of Italian historical theatres. It moved from the ISO 3382 which provides the guidelines for the measurement of a well established set of room acoustic parameters inside performance spaces. Nevertheless, the peculiarity of Italian historical theatres needs a more specific approach. The Charter of Ferrara goes in this direction, aiming at qualifying the sound field in this kind of halls and the present work pursues the way forward. Trying to understand how the acoustical qualification should be done, the Bonci Theatre in Cesena has been taken as a case study. In September 2012 acoustical measurements were carried out in the theatre, recording monaural e binaural impulse responses at each seat in the hall. The values of the time criteria, energy criteria and psycho-acoustical and spatial criteria have been extracted according to ISO 3382. Statistics were performed and a 3D model of the theatre was realised and tuned. Statistical investigations were carried out on the whole set of measurement positions and on carefully chosen reduced subsets; it turned out that these subsets are representative only of the “average” acoustics of the hall. Normality tests were carried out to verify whether EDT, T30 and C80 could be described with some degree of reliability with a theoretical distribution. Different results, according to the varying assumptions underlying each test, were found. Finally, an attempt was made to correlate the numerical results emerged from the statistical analysis to the perceptual sphere. Looking for “acoustical equivalent areas”, relative difference limens were considered as threshold values. No rule of thumb emerged. Finally, the significance of the usual representation through mean values and standard deviation, which may be meaningful for normal distributed data, was investigated.