Scalable Large-Margin Structured Learning: Theory and Algorithms

Much of NLP tries to map structured input (sentences) to some form of structured output (tag sequences, parse trees, semantic graphs, or translated/paraphrased/compressed sentences). Thus structured prediction and its learning algorithm are of central importance to us NLP researchers. However, when applying machine learning to structured domains, we often face scalability issues for two reasons:

Paper

Full text

PDF

Scalable Large-Margin Structured Learning: Theory and Algorithms

Semantic Scholar · Computer Science · 2014

Abstract

Much of NLP tries to map structured input (sentences) to some form of structured output (tag sequences, parse trees, semantic graphs, or translated/paraphrased/compressed sentences). Thus structured prediction and its learning algorithm are of central importance to us NLP researchers. However, when applying machine learning to structured domains, we often face scalability issues for two reasons:

References (2)

01@BULLET Multiclass Perceptron (and voted/average perceptron) @BULLET Freund and Schapire1999 · @BULLET Multiclass Perceptron (and voted/average perceptron) @BULLET Freund and Schapire
02References (1) @BULLET Binary Perceptron @BULLET original: Rosenblatt, 1959 @BULLET convergence proof: Novikoff1962 · References (1) @BULLET Binary Perceptron @BULLET original: Rosenblatt, 1959 @BULLET convergence proof: Novikoff

Similar papers

© 2026 NYSGPT2525 LLC