Working with a small dataset - semi-supervised dependency parsing for Irish

Teresa Lynn; Jennifer Foster; Mark Dras; Josef van Genabith

Working with a small dataset - semi-supervised dependency parsing for Irish

Teresa Lynn, Jennifer Foster, Mark Dras, Josef van Genabith

Department of Computing

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

3 Citations (Scopus)

Abstract

We present a number of semi-supervised parsing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semi-supervised learning in the form of self-training and co-training yields only very modest improvements in parsing accuracy. We also try to use morphological information in a targeted way and fail to see any improvements.

Original language	English
Title of host publication	SPMRL 2013
Subtitle of host publication	Fourth Workshop on Statistical Parsing of Morphologically Rich Languages : proceedings of the the workshop
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics
Pages	1-11
Number of pages	11
ISBN (Print)	9781937284978
Publication status	Published - 2013
Event	Workshop on Statistical Parsing of Morphologically Rich Languages (4th : 2013) - Seattle, WA Duration: 18 Oct 2013 → 21 Oct 2013

Workshop

Workshop	Workshop on Statistical Parsing of Morphologically Rich Languages (4th : 2013)
City	Seattle, WA
Period	18/10/13 → 21/10/13

Fingerprint Dive into the research topics of 'Working with a small dataset - semi-supervised dependency parsing for Irish'. Together they form a unique fingerprint.

Cite this

@inproceedings{0daa0e6e57c94be1a1fcf4f7a4b685da,

title = "Working with a small dataset - semi-supervised dependency parsing for Irish",

abstract = "We present a number of semi-supervised parsing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semi-supervised learning in the form of self-training and co-training yields only very modest improvements in parsing accuracy. We also try to use morphological information in a targeted way and fail to see any improvements.",

author = "Teresa Lynn and Jennifer Foster and Mark Dras and {van Genabith}, Josef",

year = "2013",

language = "English",

isbn = "9781937284978",

pages = "1--11",

booktitle = "SPMRL 2013",

publisher = "Association for Computational Linguistics",

}

Lynn, T, Foster, J, Dras, M & van Genabith, J 2013, Working with a small dataset - semi-supervised dependency parsing for Irish. in SPMRL 2013: Fourth Workshop on Statistical Parsing of Morphologically Rich Languages : proceedings of the the workshop. Association for Computational Linguistics, Stroudsburg, PA, pp. 1-11, Workshop on Statistical Parsing of Morphologically Rich Languages (4th : 2013), Seattle, WA, 18/10/13.

Working with a small dataset - semi-supervised dependency parsing for Irish. / Lynn, Teresa; Foster, Jennifer; Dras, Mark; van Genabith, Josef.

SPMRL 2013: Fourth Workshop on Statistical Parsing of Morphologically Rich Languages : proceedings of the the workshop. Stroudsburg, PA : Association for Computational Linguistics, 2013. p. 1-11.

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

TY - GEN

T1 - Working with a small dataset - semi-supervised dependency parsing for Irish

AU - Lynn, Teresa

AU - Foster, Jennifer

AU - Dras, Mark

AU - van Genabith, Josef

PY - 2013

Y1 - 2013

N2 - We present a number of semi-supervised parsing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semi-supervised learning in the form of self-training and co-training yields only very modest improvements in parsing accuracy. We also try to use morphological information in a targeted way and fail to see any improvements.

AB - We present a number of semi-supervised parsing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semi-supervised learning in the form of self-training and co-training yields only very modest improvements in parsing accuracy. We also try to use morphological information in a targeted way and fail to see any improvements.

M3 - Conference proceeding contribution

SN - 9781937284978

SP - 1

EP - 11

BT - SPMRL 2013

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

ER -