Margin-based decomposed amortized inference

Gourab Kundu, Vivek Srikumar, Dan Roth

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Given that structured output prediction is typically performed over entire datasets, one natural question is whether it is possible 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 previous solutions are provably optimal. Second, we introduce decomposed amortized inference, which is designed to address very large inference problems, where earlier amortization methods become less effective. This approach works by decomposing the output structure and applying amortization piece-wise, thus increasing the chance that we can re-use previous solutions for parts of the output structure. These parts are then combined to a global coherent solution using Lagrangian relaxation. In our experiments, using the NLP tasks of semantic role labeling and entityrelation extraction, we demonstrate that with the margin-based algorithm, we need to call the inference engine only for a third of the test examples. Further, we show that the decomposed variant of margin-based amortized inference achieves a greater reduction in the number of inference calls.

Original languageEnglish (US)
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages905-913
Number of pages9
ISBN (Print)9781937284503
StatePublished - Jan 1 2013
Event51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria
Duration: Aug 4 2013Aug 9 2013

Publication series

NameACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Volume1

Other

Other51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
CountryBulgaria
CitySofia
Period8/4/138/9/13

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Margin-based decomposed amortized inference'. Together they form a unique fingerprint.

  • Cite this

    Kundu, G., Srikumar, V., & Roth, D. (2013). Margin-based decomposed amortized inference. In Long Papers (pp. 905-913). (ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference; Vol. 1). Association for Computational Linguistics (ACL).