Paper: Margin-based Decomposed Amortized Inference

ACL ID P13-1089
Title Margin-based Decomposed Amortized Inference
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2013

Given that structured output prediction is typically performed over entire datasets, one natural question is whether it is pos- sible to re-use computation from earlier inference instances to speed up inference for future instances. Amortized inference has been proposed as a way to accomplish this. In this paper, first, we introduce a new amortized inference algorithm called the Margin-based Amortized Inference, which uses the notion of structured margin to identify inference problems for which pre- vious solutions are provably optimal. Sec- ond, we introduce decomposed amortized inference, which is designed to address very large inference problems, where ear- lier amortization methods become less ef- fective. This approach works by decom- posing the output structure and applying amortizat...