177 citations · 392 across the 27 of their papers we have counts for
5 papers · 1 filter
Learning to Segment Inputs for NMT Favors Character-Level Processing
Julia Kreutzer, Artem Sokolov
Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the m…
Explaining and Generalizing Back-Translation through Wake-Sleep
Ryan Cotterell, Julia Kreutzer
Back-translation has become a commonly employed heuristic for semi-supervised neural machine translation. The technique is both straightforward to apply and has led to state-of-the…
A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
Tsz Kin Lam, Julia Kreutzer, Stefan Riezler
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to sele…
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
Julia Kreutzer, Joshua Uyheng, Stefan Riezler
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 translation (NMT).…
Can Neural Machine Translation be Improved with User Feedback?
Julia Kreutzer, Shahram Khadivi, Evgeny Matusov +1
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collect…