Year: 2017
Type: conference-paper
Abstract: Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback.This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures.We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks.Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization.We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.
DOI: 10.18653/v1/p17-1138
Authors: Julia Kreutzer, Artem Sokolov, Stefan Riezler
Institutions: Heidelberg University, Amazon (United States)
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
Funder: Deutsche Forschungsgemeinschaft
OpenAlex ID: W2609616693
