Advanced

Logistic Online Online Learning Methods and Their Application to Incremental Dependency Parsing

Johansson, Richard LU (2007) ACL 2007 Student Research Workshop In Proceedings of the ACL 2007 Student Research Workshop p.49-54
Abstract
We investigate a family of update methods for online machine learning algorithms for cost-sensitive multiclass and structured classification problems. The update rules are based on multinomial logistic models. The most interesting question for such an approach is how to integrate the cost function into the learning paradigm. We propose a number of solutions to this problem.



To demonstrate the applicability of the algorithms, we evaluated them on a number of classification tasks related to incremental dependency parsing. These tasks were conventional multiclass classification, hiearchical classification, and a structured classification task: complete labeled dependency tree prediction. The performance figures of the... (More)
We investigate a family of update methods for online machine learning algorithms for cost-sensitive multiclass and structured classification problems. The update rules are based on multinomial logistic models. The most interesting question for such an approach is how to integrate the cost function into the learning paradigm. We propose a number of solutions to this problem.



To demonstrate the applicability of the algorithms, we evaluated them on a number of classification tasks related to incremental dependency parsing. These tasks were conventional multiclass classification, hiearchical classification, and a structured classification task: complete labeled dependency tree prediction. The performance figures of the logistic algorithms range from slightly lower to slightly higher than margin-based online algorithms. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Machine learning, natural language processing
in
Proceedings of the ACL 2007 Student Research Workshop
pages
6 pages
publisher
Association for Computational Linguistics
conference name
ACL 2007 Student Research Workshop
language
English
LU publication?
yes
id
65378d3c-a74d-4594-956c-92778798bd8c (old id 630085)
alternative location
http://www.aclweb.org/anthology-new/P/P07/P07-3009.pdf
date added to LUP
2007-11-27 13:38:09
date last changed
2016-04-16 09:51:36
@misc{65378d3c-a74d-4594-956c-92778798bd8c,
  abstract     = {We investigate a family of update methods for online machine learning algorithms for cost-sensitive multiclass and structured classification problems. The update rules are based on multinomial logistic models. The most interesting question for such an approach is how to integrate the cost function into the learning paradigm. We propose a number of solutions to this problem.<br/><br>
<br/><br>
To demonstrate the applicability of the algorithms, we evaluated them on a number of classification tasks related to incremental dependency parsing. These tasks were conventional multiclass classification, hiearchical classification, and a structured classification task: complete labeled dependency tree prediction. The performance figures of the logistic algorithms range from slightly lower to slightly higher than margin-based online algorithms.},
  author       = {Johansson, Richard},
  keyword      = {Machine learning,natural language processing},
  language     = {eng},
  pages        = {49--54},
  publisher    = {ARRAY(0x9942c50)},
  series       = {Proceedings of the ACL 2007 Student Research Workshop},
  title        = {Logistic Online Online Learning Methods and Their Application to Incremental Dependency Parsing},
  year         = {2007},
}