Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Posts by Year
This blog post gives an overview of the paper “Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs”.
Introducing Joey NMT, a minimalist neural machine translation framework for novices built on Pytorch.
This post presents a summary of my PhD thesis. I explored how to learn from feedback given to model outputs when the collection of direct supervision signals...
How can we give RL agents that learn from human feedback a possible advantage to succeed in this difficult learning scenario?
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?
This post explains the need for the score function gradient estimator trick and how it works.