<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation?"^^ . "Through globalization of the industry and the collaboration of nations world wide theimportance of machine translated documents is rising. Many new ideas and conceptswere proposed in the recent years to improve the overall quality of machine translation(MT). A lot of focus in machine learning is going towards the research of alternativelearning techniques, as the basic existing paradigms such as supervised, unsupervised andreinforcement learning are not a perfect fit for every task. Imitation learning is a techniquewhich combines the exploratory aspect of reinforcement with the efficiency of supervisedlearning. Through the usage of an interactive expert, the learning model, also calledstudent, is able to obtain intermediate feedback for it’s predictions at any given point intime. Thereby the student is aware of it’s mistakes by considering the difference of it’s andthe expert’s prediction from this point. Imitation learning can improve all major problemsfor training artificial neural networks given the right expert. These are: the time it takesto train a model, the acquisition of data and most importantly the overall performancegiven some specific metric.The most common quality evaluation metric used for MT is BLEU. It is based on then-gram precision between the generated translation, given some input, and the referencetranslation. Therefore it is non-differentiable and can not be used as a loss to train a MTmodel directly. For the training usually the maximum likelihood estimation (MLE) is used,such that the likelihood of each token in the output, given the input sequence, is maximized.This creates a discrepancy between training (MLE) and validation objective (BLEU). Thisthesis tries to overcome this issue by directly learning on the differences of the expectedBLEU from the student and the expert in an imitation learning scenario. The expert isrepresented by a traditional statistical machine translation (SMT) model that should helpthe student in solving the problems mentioned above. For this a novel data aggregationmethodAggregateData using approximatedBLEUexplorations (ADBLEU) based onimitation learning was implemented. After conducting several experiments, validatingdifferent approaches of data aggregation, it is shown that it is not possible to significantlyimprove the state-of-the-art student, due to limitations of the SMT expert."^^ . "2021" . . . . . . . "Luca"^^ . "Hormann"^^ . "Luca Hormann"^^ . . . . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (PDF)"^^ . . . "Master_Thesis.pdf"^^ . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (Other)"^^ . . . . . . "preview.jpg"^^ . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (Other)"^^ . . . . . . "medium.jpg"^^ . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (Other)"^^ . . . . . . "small.jpg"^^ . . . "Can oracle-based imitation learning improveneural machine translation with dataaggregation? (Other)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #30516 \n\nCan oracle-based imitation learning improveneural machine translation with dataaggregation?\n\n" . "text/html" . . . "004 Informatik"@de . "004 Data processing Computer science"@en . .