Learning the morphology of Zulu with different degrees of supervision

Spiegler Sebastian; Golenia Bruno; Shalonova Ksenia; Peter Flach; Tucker Roger

Learning the morphology of Zulu with different degrees of supervision

Spiegler Sebastian, Golenia Bruno, Shalonova Ksenia, Peter Flach, Tucker Roger

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

7 Citations (Scopus)

Abstract

In this paper we compare different levels of supervision for learning the morphology of the indigenous South African language Zulu. After a preliminary analysis of the Zulu data used for our experiments, we concentrate on supervised, semi-supervised and unsupervised approaches comparing strengths and weaknesses of each method. The challenges we face are limited data availability and data sparsity in connection with morphological analysis of indigenous languages. At the end of the paper we draw conclusions for our future work towards a morphological analyzer for Zulu.

Translated title of the contribution	Learning the morphology of Zulu with different degrees of supervision
Original language	English
Title of host publication	Spoken Language Technology Workshop, 2008
Pages	9-12
Publication status	Published - 2008

Bibliographical note

ISBN: 9781424434718
Publisher: IEEE
Name and Venue of Conference: Spoken Language Technology Workshop, 2008. SLT 2008. IEEE
Other identifier: 2000994

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2000994

Fingerprint Dive into the research topics of 'Learning the morphology of Zulu with different degrees of supervision'. Together they form a unique fingerprint.

Cite this

@inproceedings{1765b970d99c4d03adcb37ff2ed17c5b,

title = "Learning the morphology of Zulu with different degrees of supervision",

abstract = " In this paper we compare different levels of supervision for learning the morphology of the indigenous South African language Zulu. After a preliminary analysis of the Zulu data used for our experiments, we concentrate on supervised, semi-supervised and unsupervised approaches comparing strengths and weaknesses of each method. The challenges we face are limited data availability and data sparsity in connection with morphological analysis of indigenous languages. At the end of the paper we draw conclusions for our future work towards a morphological analyzer for Zulu. ",

author = "Spiegler Sebastian and Golenia Bruno and Shalonova Ksenia and Peter Flach and Tucker Roger",

note = "ISBN: 9781424434718 Publisher: IEEE Name and Venue of Conference: Spoken Language Technology Workshop, 2008. SLT 2008. IEEE Other identifier: 2000994",

year = "2008",

language = "English",

pages = "9--12",

booktitle = "Spoken Language Technology Workshop, 2008",

}

TY - GEN

T1 - Learning the morphology of Zulu with different degrees of supervision

AU - Sebastian, Spiegler

AU - Bruno, Golenia

AU - Ksenia, Shalonova

AU - Flach, Peter

AU - Roger, Tucker

N1 - ISBN: 9781424434718 Publisher: IEEE Name and Venue of Conference: Spoken Language Technology Workshop, 2008. SLT 2008. IEEE Other identifier: 2000994

PY - 2008

Y1 - 2008

N2 - In this paper we compare different levels of supervision for learning the morphology of the indigenous South African language Zulu. After a preliminary analysis of the Zulu data used for our experiments, we concentrate on supervised, semi-supervised and unsupervised approaches comparing strengths and weaknesses of each method. The challenges we face are limited data availability and data sparsity in connection with morphological analysis of indigenous languages. At the end of the paper we draw conclusions for our future work towards a morphological analyzer for Zulu.

AB - In this paper we compare different levels of supervision for learning the morphology of the indigenous South African language Zulu. After a preliminary analysis of the Zulu data used for our experiments, we concentrate on supervised, semi-supervised and unsupervised approaches comparing strengths and weaknesses of each method. The challenges we face are limited data availability and data sparsity in connection with morphological analysis of indigenous languages. At the end of the paper we draw conclusions for our future work towards a morphological analyzer for Zulu.

M3 - Conference Contribution (Conference Proceeding)

SP - 9

EP - 12

BT - Spoken Language Technology Workshop, 2008

ER -