6 citations · 34 across the 18 of their papers we have counts for
3 papers · 1 filter
Attending to Future Tokens For Bidirectional Sequence Generation
Carolin Lawrence, Bhushan Kotnis, Mathias Niepert
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In c…
Counterfactual Learning for Machine Translation: Degeneracies and Solutions
Carolin Lawrence, Pratik Gajane, Stefan Riezler
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…
Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation
Carolin Lawrence, Artem Sokolov, Stefan Riezler
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that…