Abstract | ||
---|---|---|
Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning. In our setting, the beam is part of the model, and not just an artifact of approximate decoding. Our meta-algorithm captures existing learning algorithms and suggests new ones. It also lets us show novel no-regret guarantees for learning beam search policies. |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | learning algorithms,structured prediction,beam search |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
2 | 0.36 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Negrinho, Renato | 1 | 2 | 1.38 |
Matthew Gormley | 2 | 84 | 10.25 |
Geoffrey J. Gordon | 3 | 3430 | 265.37 |