In recent years some researchers have explored the use of reinforcement learning (RL)
algorithms as key components in the solution of various natural language processing (NLP) …

Reinforcement learning (RL) techniques optimize the accumulated long-term reward of a
suitably chosen reward function. However, designing such a reward function often requires …

Machine translation is a natural candidate problem for reinforcement learning from human
feedback: users provide quick, dirty ratings on candidate translations to guide a system to …

Children start to communicate and use language in social interactions from a very young
age. This allows them to experiment with their developing linguistic knowledge and receive …

We present a study on reinforcement learning (RL) from human bandit feedback for
sequence-to-sequence learning, exemplified by the task of bandit neural machine …

Insufficient modeling of human preferences within the reward model is a major obstacle for
leveraging human feedback to improve translation quality. Fortunately, quality estimation …

We propose a method to perform automatic document summarisation without using
reference summaries. Instead, our method interactively learns from users' preferences. The …

Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers
are still a tedious process with challenges such as costly data annotation and privacy risks …

We study learning from user feedback for extractive question answering by simulating
feedback using supervised data. We cast the problem as contextual bandit learning, and …

Bandit structured prediction describes a stochastic optimization framework where learning is
performed from partial feedback. This feedback is received in the form of a task loss …