Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Accurate Maximum-Margin Training for Parsing With Context-Free Grammars

Authors
Bauer, AlexanderBraun, MikioMueller, Klaus-Robert
Issue Date
1월-2017
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Context-free grammar (CFG); dynamic programming; inference; margin rescaling (MR); natural language parsing; probabilistic context-free grammar (PCFG); slack rescaling (SR); structural support vector machines (SVMs); structured output
Citation
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, v.28, no.1, pp.44 - 56
Indexed
SCIE
SCOPUS
Journal Title
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume
28
Number
1
Start Page
44
End Page
56
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/84976
DOI
10.1109/TNNLS.2015.2497149
ISSN
2162-237X
Abstract
The task of natural language parsing can naturally be embedded in the maximum-margin framework for structured output prediction using an appropriate joint feature map and a suitable structured loss function. While there are efficient learning algorithms based on the cutting-plane method for optimizing the resulting quadratic objective with potentially exponential number of linear constraints, their efficiency crucially depends on the inference algorithms used to infer the most violated constraint in a current iteration. In this paper, we derive an extension of the well-known Cocke-Kasami-Younger (CKY) algorithm used for parsing with probabilistic context-free grammars for the case of loss-augmented inference enabling an effective training in the cutting-plane approach. The resulting algorithm is guaranteed to find an optimal solution in polynomial time exceeding the running time of the CKY algorithm by a term, which only depends on the number of possible loss values. In order to demonstrate the feasibility of the presented algorithm, we perform a set of experiments for parsing English sentences.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE