Year: 2016
Type: conference-paper
Abstract: Structured prediction from bandit feedback describes a learning scenario where instead of having access to a gold standard structure, a learner only receives partial feedback in form of the loss value of a predicted structure.We present new learning objectives and algorithms for this interactive scenario, focusing on convergence speed and ease of elicitability of feedback.We present supervised-to-bandit simulation experiments for several NLP tasks (machine translation, sequence labeling, text classification), showing that bandit learning from relative preferences eases feedback strength and yields improved empirical convergence.
DOI: 10.18653/v1/p16-1152
Authors: Artem Sokolov, Julia Kreutzer, Christopher Lo, Stefan Riezler
Institution: Heidelberg University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W2513592723
