03496ntm a22005297i 4500 000260361 CZ-PrVSE 20221108171029.0 m d cr n|||||||||| 221108s2022 xr fsbm 000 0 eng d NEZPRACOVANÝ IMPORT ABA006 cze ABA006 ABA006 rda Dvořák, Jáchym ISIS:115341 dis GPT-2 pro klasifikaci emailů v němčině na platformě Azure eng GPT-2 for email classification of german emails in Azure / Jáchym Dvořák 2022 ?? stran : digital, PDF soubor Vedoucí práce: Pavel Zimmermann Diplomová práce (Ing.)—Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky, 2022 Obsahuje bibliografii Textový (vysokoškolská kvalifikační práce) Rok obhajoby 2022 Siemens currently uses a machine learning system deployed in the Azure cloud platform that categorizes incoming emails in German into several categories, subcategories and assigns priority to them. However, full try-out of different models has not been performed, and despite great industry-wise performance of the current solution, it is not clear whether it can be improved. This thesis outlines the theoretical pillars required for understanding the practical part, in which it investigates whether improving performance is possible using a different model and an ensemble solution, tackles other relevant tasks such as assessing whether the data changes over time and presents results in comparison with the current solution. While the analysis shows that performance does not improve with a different, state-of-the-art model, it further strengthens the position of the current model as the optimal solution, and the suggested GPT-2 model may outperform the current DistilBERT in future use-cases. Additionally, the ensemble method, consisting of combining the current and proposed solutions, shows promising results in one of the three tasks, improving prediction accuracy by half a percent. Furthermore, several improvements in the code-base as well as further knowledge about the problem as a result of this experiment are likely to help the business in the future. Způsob přístupu: Internet data a analytika pro business [obor dipl. práce] diplomové práce fd132022 czenas master's theses eczenas Machine Learning GPT-2 Azure Natural Language Processing (NLP) Zimmermann, Pavel, 1980- jo20251268570 ths Habarta, Filip ISIS:99500 opn Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky kn20010709399 dgg https://insis.vse.cz/zp/79513/podrobnosti VŠKP v InSIS https://insis.vse.cz/zp/79513 Hlavní práce https://insis.vse.cz/zp/79513/posudek/vedouci Hodnocení vedoucího https://insis.vse.cz/zp/79513/posudek/oponent/74301 Oponentura https://insis.vse.cz/zp/79513/priloha/23592 Přiloha k práci https://insis.vse.cz/zp/79513/priloha/23598 Přiloha k práci https://insis.vse.cz/zp/79513/podrobnosti dc:identifier NEPOSILAT VSKP vse79513 221013 79513