Online learning via global feedback for phrase recognition

Xavier Carreras, Lluis Marques

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

3 Citations (Scopus)

Abstract

This work presents an architecture based on perceptrons to recognize phrase structures, and an online learning algorithm to train the perceptrons together and dependently. The recognition strategy applies learning in two layers: a filtering layer, which reduces the search space by identifying plausible phrase candidates, and a ranking layer, which recursively builds the optimal phrase structure. We provide a recognition-based feedback rule which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. Experimentation on a syntactic parsing problem, the recognition of clause hierarchies, improves state-of-the-art results and evinces the advantages of our global training method over optimizing each function locally and independently.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
ISBN (Print)0262201526, 9780262201520
Publication statusPublished - 1 Jan 2004
Externally publishedYes
Event17th Annual Conference on Neural Information Processing Systems, NIPS 2003 - Vancouver, BC, Canada
Duration: 8 Dec 200313 Dec 2003

Other

Other17th Annual Conference on Neural Information Processing Systems, NIPS 2003
CountryCanada
CityVancouver, BC
Period8/12/0313/12/03

Fingerprint

Neural networks
Feedback
Syntactics
Learning algorithms

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Carreras, X., & Marques, L. (2004). Online learning via global feedback for phrase recognition. In Advances in Neural Information Processing Systems Neural information processing systems foundation.

Online learning via global feedback for phrase recognition. / Carreras, Xavier; Marques, Lluis.

Advances in Neural Information Processing Systems. Neural information processing systems foundation, 2004.

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

Carreras, X & Marques, L 2004, Online learning via global feedback for phrase recognition. in Advances in Neural Information Processing Systems. Neural information processing systems foundation, 17th Annual Conference on Neural Information Processing Systems, NIPS 2003, Vancouver, BC, Canada, 8/12/03.
Carreras X, Marques L. Online learning via global feedback for phrase recognition. In Advances in Neural Information Processing Systems. Neural information processing systems foundation. 2004
Carreras, Xavier ; Marques, Lluis. / Online learning via global feedback for phrase recognition. Advances in Neural Information Processing Systems. Neural information processing systems foundation, 2004.
@inproceedings{438793d58bee4a5786f7f02064f33066,
title = "Online learning via global feedback for phrase recognition",
abstract = "This work presents an architecture based on perceptrons to recognize phrase structures, and an online learning algorithm to train the perceptrons together and dependently. The recognition strategy applies learning in two layers: a filtering layer, which reduces the search space by identifying plausible phrase candidates, and a ranking layer, which recursively builds the optimal phrase structure. We provide a recognition-based feedback rule which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. Experimentation on a syntactic parsing problem, the recognition of clause hierarchies, improves state-of-the-art results and evinces the advantages of our global training method over optimizing each function locally and independently.",
author = "Xavier Carreras and Lluis Marques",
year = "2004",
month = "1",
day = "1",
language = "English",
isbn = "0262201526",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - Online learning via global feedback for phrase recognition

AU - Carreras, Xavier

AU - Marques, Lluis

PY - 2004/1/1

Y1 - 2004/1/1

N2 - This work presents an architecture based on perceptrons to recognize phrase structures, and an online learning algorithm to train the perceptrons together and dependently. The recognition strategy applies learning in two layers: a filtering layer, which reduces the search space by identifying plausible phrase candidates, and a ranking layer, which recursively builds the optimal phrase structure. We provide a recognition-based feedback rule which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. Experimentation on a syntactic parsing problem, the recognition of clause hierarchies, improves state-of-the-art results and evinces the advantages of our global training method over optimizing each function locally and independently.

AB - This work presents an architecture based on perceptrons to recognize phrase structures, and an online learning algorithm to train the perceptrons together and dependently. The recognition strategy applies learning in two layers: a filtering layer, which reduces the search space by identifying plausible phrase candidates, and a ranking layer, which recursively builds the optimal phrase structure. We provide a recognition-based feedback rule which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. Experimentation on a syntactic parsing problem, the recognition of clause hierarchies, improves state-of-the-art results and evinces the advantages of our global training method over optimizing each function locally and independently.

UR - http://www.scopus.com/inward/record.url?scp=84898955511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898955511&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0262201526

SN - 9780262201520

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -