Cover Image

Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger

This paper is concerned with the application of technologies developed in other disciplines, in particular with the use of text processing techniques to investigate the problems of second language learner writing in English. The question addressed is whether learner texts produced by L1-Malay lea...

Full description

Saved in:
Bibliographic Details
Main Authors: Roslina Abdul Aziz,, Zuraidah Mohd Don,
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2019
Online Access:http://journalarticle.ukm.my/14094/1/30438-108026-1-PB.pdf
http://journalarticle.ukm.my/14094/
http://ejournal.ukm.my/gema/issue/view/1212
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-ukm.journal.14094
record_format eprints
spelling my-ukm.journal.140942020-01-31T22:50:17Z http://journalarticle.ukm.my/14094/ Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger Roslina Abdul Aziz, Zuraidah Mohd Don, This paper is concerned with the application of technologies developed in other disciplines, in particular with the use of text processing techniques to investigate the problems of second language learner writing in English. The question addressed is whether learner texts produced by L1-Malay learners at the University of Malaya can usefully be processed using the Constituent Likelihood Automatic Word-tagging System (CLAWS); a part-of-speech (POS) tagger developed for and trained on texts written by native speakers of the language. The study adopts the procedure employed by van Rooy and Schäfer (2002).CLAWS was used to automatically POS tag a subset of the Malaysian Corpus of Learner English (MACLE), and the texts were then analyzed for tagging accuracy.CLAWS was found to perform less well on learner text than on native speaker texts, but still with an accuracy rate of over 90%. The sources of error are traced, and spelling errors are found to be the most common source. Closer inspection indicates that successful tagging is likely to lead to problems downstream in later processing, which suggests that to optimize performance, some modifications will be required in tagger design. Penerbit Universiti Kebangsaan Malaysia 2019-08 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/14094/1/30438-108026-1-PB.pdf Roslina Abdul Aziz, and Zuraidah Mohd Don, (2019) Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger. GEMA: Online Journal of Language Studies, 19 (3). pp. 140-155. ISSN 1675-8021 http://ejournal.ukm.my/gema/issue/view/1212
institution Universiti Kebangsaan Malaysia
building Tun Sri Lanang Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Kebangsaan Malaysia
content_source UKM Journal Article Repository
url_provider http://journalarticle.ukm.my/
language English
description This paper is concerned with the application of technologies developed in other disciplines, in particular with the use of text processing techniques to investigate the problems of second language learner writing in English. The question addressed is whether learner texts produced by L1-Malay learners at the University of Malaya can usefully be processed using the Constituent Likelihood Automatic Word-tagging System (CLAWS); a part-of-speech (POS) tagger developed for and trained on texts written by native speakers of the language. The study adopts the procedure employed by van Rooy and Schäfer (2002).CLAWS was used to automatically POS tag a subset of the Malaysian Corpus of Learner English (MACLE), and the texts were then analyzed for tagging accuracy.CLAWS was found to perform less well on learner text than on native speaker texts, but still with an accuracy rate of over 90%. The sources of error are traced, and spelling errors are found to be the most common source. Closer inspection indicates that successful tagging is likely to lead to problems downstream in later processing, which suggests that to optimize performance, some modifications will be required in tagger design.
format Article
author Roslina Abdul Aziz,
Zuraidah Mohd Don,
spellingShingle Roslina Abdul Aziz,
Zuraidah Mohd Don,
Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
author_facet Roslina Abdul Aziz,
Zuraidah Mohd Don,
author_sort Roslina Abdul Aziz,
title Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
title_short Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
title_full Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
title_fullStr Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
title_full_unstemmed Tagging L2 writing: learner errors and the performance of an automated part-of-speech tagger
title_sort tagging l2 writing: learner errors and the performance of an automated part-of-speech tagger
publisher Penerbit Universiti Kebangsaan Malaysia
publishDate 2019
url http://journalarticle.ukm.my/14094/1/30438-108026-1-PB.pdf
http://journalarticle.ukm.my/14094/
http://ejournal.ukm.my/gema/issue/view/1212
_version_ 1657565467026391040
score 13.211869

Similar Items