Counterfactual Learning for Machine Translation: Degeneracies and Solutions

11/23/2017
by   Carolin Lawrence, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/28/2017

Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation

The goal of counterfactual learning for statistical machine translation ...
research
05/03/2018

Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback

Counterfactual learning from human bandit feedback describes a scenario ...
research
02/23/2023

Sequential Counterfactual Risk Minimization

Counterfactual Risk Minimization (CRM) is a framework for dealing with t...
research
12/04/2022

Counterfactual Learning with General Data-generating Policies

Off-policy evaluation (OPE) attempts to predict the performance of count...
research
11/26/2017

Machine Translation Using Semantic Web Technologies: A Survey

A large number of machine translation approaches has been developed rece...
research
07/23/2019

Semantic Web for Machine Translation: Challenges and Directions

A large number of machine translation approaches have recently been deve...
research
11/29/2018

Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing

In semantic parsing for question-answering, it is often too expensive to...

Please sign up or login with your details

Forgot password? Click here to reset