Training a Log-Linear Parser with Loss Functions via Softmax-Margin

Michael Auli, Adam Lopez

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

Abstract

Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like F- measure. Softmax-margin is a convex objective for such models that minimises a bound on expected risk for a given loss function, but its näıve application requires the loss to decompose over the predicted structure, which is not true of F-measure. We use softmax-margin to optimise a log-linear CCG parser for a variety of loss functions, and demonstrate a novel dynamic programming algorithm that enables us to use it with F-measure, leading to substantial gains in accuracy on CCG- Bank. When we embed our loss-trained parser into a larger model that includes supertagging features incorporated via belief propagation, we obtain further improvements and achieve a labelled/unlabelled dependency F-measure of 89.3%/94.0% on gold part-of-speech tags, and 87.2%/92.8% on automatic part-of-speech tags, the best reported results for this task.
Original languageEnglish
Title of host publicationProceedings of the 2011 Conference on Empirical Methods in Natural Language Processing
Place of PublicationEdinburgh, Scotland, UK.
PublisherAssociation for Computational Linguistics
Pages333-343
Number of pages11
Publication statusPublished - 1 Jul 2011

Fingerprint

Dive into the research topics of 'Training a Log-Linear Parser with Loss Functions via Softmax-Margin'. Together they form a unique fingerprint.

Cite this