Non-linear tagging models with localist and distributed word representations

Sumit Chopra; Srinivas Bangalore

doi:10.1109/ICASSP.2011.5946751

Non-linear tagging models with localist and distributed word representations

Sumit Chopra, Srinivas Bangalore

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are divorced from the task context. In this paper, we describe a model that learns distributed representations of words in order to optimize task performance. We investigate this model for part-of-speech tagging and supertagging tasks and demonstrate its superior accuracy over localist models, especially for rare words. We also show that adding non-linearity in the model aids in improved accuracy for complex tasks such as supertagging.

Original language	English (US)
Title of host publication	2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
Pages	2144-2147
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2011.5946751
State	Published - 2011
Event	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic Duration: May 22 2011 → May 27 2011

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Other

Other	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Country/Territory	Czech Republic
City	Prague
Period	5/22/11 → 5/27/11

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2011.5946751

Cite this

Chopra, S., & Bangalore, S. (2011). Non-linear tagging models with localist and distributed word representations. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings (pp. 2144-2147). Article 5946751 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2011.5946751

Non-linear tagging models with localist and distributed word representations. / Chopra, Sumit; Bangalore, Srinivas.
2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 2144-2147 5946751 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chopra, S & Bangalore, S 2011, Non-linear tagging models with localist and distributed word representations. in 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings., 5946751, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 2144-2147, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 5/22/11. https://doi.org/10.1109/ICASSP.2011.5946751

Chopra S, Bangalore S. Non-linear tagging models with localist and distributed word representations. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 2144-2147. 5946751. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2011.5946751

@inproceedings{44d46daa0b0344b2a88bf2efd9d17ca5,

title = "Non-linear tagging models with localist and distributed word representations",

abstract = "Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are divorced from the task context. In this paper, we describe a model that learns distributed representations of words in order to optimize task performance. We investigate this model for part-of-speech tagging and supertagging tasks and demonstrate its superior accuracy over localist models, especially for rare words. We also show that adding non-linearity in the model aids in improved accuracy for complex tasks such as supertagging.",

author = "Sumit Chopra and Srinivas Bangalore",

year = "2011",

doi = "10.1109/ICASSP.2011.5946751",

language = "English (US)",

isbn = "9781457705397",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "2144--2147",

booktitle = "2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings",

note = "36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 ; Conference date: 22-05-2011 Through 27-05-2011",

}

TY - GEN

T1 - Non-linear tagging models with localist and distributed word representations

AU - Chopra, Sumit

AU - Bangalore, Srinivas

PY - 2011

Y1 - 2011

N2 - Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are divorced from the task context. In this paper, we describe a model that learns distributed representations of words in order to optimize task performance. We investigate this model for part-of-speech tagging and supertagging tasks and demonstrate its superior accuracy over localist models, especially for rare words. We also show that adding non-linearity in the model aids in improved accuracy for complex tasks such as supertagging.

AB - Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are divorced from the task context. In this paper, we describe a model that learns distributed representations of words in order to optimize task performance. We investigate this model for part-of-speech tagging and supertagging tasks and demonstrate its superior accuracy over localist models, especially for rare words. We also show that adding non-linearity in the model aids in improved accuracy for complex tasks such as supertagging.

UR - http://www.scopus.com/inward/record.url?scp=80051651276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051651276&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5946751

DO - 10.1109/ICASSP.2011.5946751

M3 - Conference contribution

AN - SCOPUS:80051651276

SN - 9781457705397

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2144

EP - 2147

BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings

T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

Y2 - 22 May 2011 through 27 May 2011

ER -

Non-linear tagging models with localist and distributed word representations

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this