# Counterfactual Learning for Machine Translation: Degeneracies and Solutions

arXiv: https://arxiv.org/abs/1711.08621 · HTML: https://mlsanity.com/paper/1711.08621/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2017.

## Built on by (most cited first, 3 of 3)

- [Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback](https://mlsanity.com/paper/1805.01252/) (2018)
- [Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks](https://mlsanity.com/paper/2011.02511/) (2020)
- [Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing](https://mlsanity.com/paper/1811.12239/) (2018)

## Abstract (arXiv)

Counterfactual learning is a natural scenario to improve web-based machine translation services by offline learning from feedback logged during user interactions. In order to avoid the risk of showing inferior translations to users, in such scenarios mostly exploration-free deterministic logging policies are in place. We analyze possible degeneracies of inverse and reweighted propensity scoring estimators, in stochastic and deterministic settings, and relate them to recently proposed techniques for counterfactual learning under deterministic logging.