Efficient Exact Inference With Loss Augmented Objective in Structured Learning

Structural support vector machine (SVM) is an elegant approach for building complex and accurate models with structured outputs. However, its applicability relies on the availability of efficient inference algorithms-the state-of-the-art training algorithms repeatedly perform inference to compute a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transaction on neural networks and learning systems Jg. 28; H. 11; S. 2566 - 2579
Hauptverfasser: Bauer, Alexander, Nakajima, Shinichi, Muller, Klaus-Robert
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.11.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Contingency
Contingency tables
Dynamic programming
Formulations
graphical models
high-order potentials
Inference
Inference algorithms
Learning algorithms
Linear programming
Loss measurement
margin scaling (MS)
Natural language processing
Prediction algorithms
Scaling
Segmentation
slack scaling (SS)
Statistical analysis
structural support vector machines (SVMs)
structured output
Support vector machines
Training
ISSN:2162-237X, 2162-2388
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Structural support vector machine (SVM) is an elegant approach for building complex and accurate models with structured outputs. However, its applicability relies on the availability of efficient inference algorithms-the state-of-the-art training algorithms repeatedly perform inference to compute a subgradient or to find the most violating configuration. In this paper, we propose an exact inference algorithm for maximizing nondecomposable objectives due to special type of a high-order potential having a decomposable internal structure. As an important application, our method covers the loss augmented inference, which enables the slack and margin scaling formulations of structural SVM with a variety of dissimilarity measures, e.g., Hamming loss, precision and recall, F β -loss, intersection over union, and many other functions that can be efficiently computed from the contingency table. We demonstrate the advantages of our approach in natural language parsing and sequence segmentation applications.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2016.2598721