Approches quantitatives de l'analyse des pr{é}dictions en traduction automatique neuronale (TAN)
This research aims to understand the non-linear progression of NMT training for researchers optimizing learning conditions, but the specific problem and impact are vaguely described.
This paper investigates the characteristic training phases of neural machine translation (NMT) engines using OpenNMT-Py, Europarl, and INTERSECT corpora. Longitudinal analyses suggest that the progression of translations during training is not always linear, highlighting the importance of chronological progression in mapping NMT processes.
As part of a larger project on optimal learning conditions in neural machine translation, we investigate characteristic training phases of translation engines. All our experiments are carried out using OpenNMT-Py: the pre-processing step is implemented using the Europarl training corpus and the INTERSECT corpus is used for validation. Longitudinal analyses of training phases suggest that the progression of translations is not always linear. Following the results of textometric explorations, we identify the importance of the phenomena related to chronological progression, in order to map different processes at work in neural machine translation (NMT).