RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Posts by Tag
neural machine translation
Translating Middle Egyptian Hieroglyphs
This blog post gives an overview of the paper “Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs”.
Joey NMT - A Minimalist NMT Toolkit for Novices
Introducing Joey NMT, a minimalist neural machine translation framework for novices built on Pytorch.
The Real Challenge of Real-World Reinforcement Learning: The Human Factor
How can we give RL agents that learn from human feedback a possible advantage to succeed in this difficult learning scenario?
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
reinforcement learning
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Response-Based and Counterfactual Learning for Sequence-to-Sequence Tasks in NLP: An Overview
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...
The Real Challenge of Real-World Reinforcement Learning: The Human Factor
How can we give RL agents that learn from human feedback a possible advantage to succeed in this difficult learning scenario?
Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?
semantic parsing
Response-Based and Counterfactual Learning for Sequence-to-Sequence Tasks in NLP: An Overview
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...
Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
policy gradient
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
expected reward
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
sampling
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
MRT
Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
REINFORCE
Counterfactual Learning of Semantic Parsers When Even Gold Answers Are Unattainable
How can we train semantic parsers if neither question-parse nor question-answer pairs can be collected?
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
exposure bias
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
score function gradient estimator
Taming Wild Reward Functions: The Score Function Gradient Estimator Trick
This post explains the need for the score function gradient estimator trick and how it works.
human factor
The Real Challenge of Real-World Reinforcement Learning: The Human Factor
How can we give RL agents that learn from human feedback a possible advantage to succeed in this difficult learning scenario?
machine translation
Response-Based and Counterfactual Learning for Sequence-to-Sequence Tasks in NLP: An Overview
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...
beginners
Joey NMT - A Minimalist NMT Toolkit for Novices
Introducing Joey NMT, a minimalist neural machine translation framework for novices built on Pytorch.
multi-task modeling
Translating Middle Egyptian Hieroglyphs
This blog post gives an overview of the paper “Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs”.
low resource scenario
Translating Middle Egyptian Hieroglyphs
This blog post gives an overview of the paper “Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs”.
monolingual data
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
future challenges
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.
BLEU
RL in NMT: The Good, the Bad and the Ugly
Discussing good, bad and ugly practices of reinforcement learning in neural machine translation.