SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1704.06497 · 2017

Bandit Structured Prediction for Neural Sequence-to-Sequence Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1704.06497")
get_code_for_paper("1704.06497")
have("1704.06497")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1704.06497.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1704.06497.svg)](https://syntology.ai/paper/1704.06497)

Connect an agent — have() is free.