How to improve podcast discovery with NLP and Machine Learning. Capstone Project for the Diploma of Advanced Studies (DAS) in Data Science at FHNW.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Hierarchical multi-label text classification of the BlurbGenreCollection using capsule networks.

Automatic Speech Recognition (ASR) - German

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

GermEval 2019 Task 1 - Shared Task on Hierarchical Classification of Blurbs

Neural Machine Translation with Keras

Interactive multimedia captioning with Keras

Code for our paper "A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation"

[EMNLP 2017] Code for "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog"

Neural scene representation and rendering (GQN)