Natural Language Generation with Reinforcement Learning
الملخص
Natural Language Generation (NLG) is the subfield of Natural Language Processing, where the task is to produce natural language outputs. Despite the important progress fostered by the application of Deep Learning, generated texts are still inconsistent and contain factual inconsistencies. At the root cause, we argue in this thesis that deep learning models in NLG suffers from inherent flaws in algorithms, which limits their efficiency. At training time, the standard training strategy, Teacher Forcing, induces the so called exposure bias, a mismatch with inference time, where the errors accumulate. Moreover, NLG suffers from a second flaw: its the automatic evaluation does not reflect well human judgement. In this thesis, we explore how to improve both evaluation and training in NLG toward more reliable systems. In particular, we propose a Question Answering based metric. We show how this metric can be used as a reward in a Reinforcement Learning setup to improve NLG models. Toward this objective, we also explore learned rewards that are the discriminators, and introduce several new algorithms that benefit NLG during training and decoding times. In particular, we propose to combine Monte Carlo Tree Search with Generative Adversarial Networks, resulting in state-of-the-art models.
الكلمات المفتاحية
غير متوفر
التخصصات
رسائل وأطاريح مشابهة
- Natural language processing as autoregressive generation Xiang Lin · Nanyang Technological University · 2023
- Improving Human Behavior Understanding with Semi-supervised Learning Bruno Manuel Degardin · 2026
- AI-Generated Image Detection Using Multimodal Deep Learning Mamadou Keïta · 2026
- Learning semantic representations of language, vision and code for visualization-oriented dialogue Henrik Voigt · 2026
- Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning Chen, Haokun · Ludwig-Maximilians-Universität München · 2025
- On large deviations in probabilistic deep learning and generative modeling Nilsson, Viktor · KTH Royal Institute of Technology · 2025
