English

Counterfactual Learning for Machine Translation: Degeneracies and Solutions

Machine Learning 2017-12-15 v3 Computation and Language Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1711.08621,
  title  = {Counterfactual Learning for Machine Translation: Degeneracies and Solutions},
  author = {Carolin Lawrence and Pratik Gajane and Stefan Riezler},
  journal= {arXiv preprint arXiv:1711.08621},
  year   = {2017}
}

Comments

Workshop "From 'What If?' To 'What Next?'" at the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA