An empirical study for Vietnamese dependency parsing

Dat Quoc Nguyen; Mark Dras; Mark Johnson

An empirical study for Vietnamese dependency parsing

Dat Quoc Nguyen, Mark Dras, Mark Johnson

School of Computing

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

15 Citations (Scopus)

Abstract

This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.

Original language	English
Title of host publication	Australasian Language Technology Association Workshop 2016
Subtitle of host publication	proceedings of the workshop
Editors	Trevor Cohn
Place of Publication	Melbourne, Australia
Publisher	Australasian Language Technology Association
Pages	143-149
Number of pages	7
Publication status	Published - 1 Dec 2016
Event	Australasian Language Technology Association Workshop (14th : 2016) - Monash University, Caulfield, Australia Duration: 5 Dec 2016 → 7 Dec 2016

Conference

Conference	Australasian Language Technology Association Workshop (14th : 2016)
Country/Territory	Australia
City	Caulfield
Period	5/12/16 → 7/12/16

Access to Document

http://aclanthology.info/papers/an-empirical-study-for-vietnamese-dependency-parsing

Cite this

@inproceedings{9b00e91f4b074c698f8ba78b3d1692ec,

title = "An empirical study for Vietnamese dependency parsing",

abstract = "This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.",

author = "Nguyen, {Dat Quoc} and Mark Dras and Mark Johnson",

year = "2016",

month = dec,

day = "1",

language = "English",

pages = "143--149",

editor = "Trevor Cohn",

booktitle = "Australasian Language Technology Association Workshop 2016",

publisher = "Australasian Language Technology Association",

note = "Australasian Language Technology Association Workshop (14th : 2016) ; Conference date: 05-12-2016 Through 07-12-2016",

}

Nguyen, DQ, Dras, M & Johnson, M 2016, An empirical study for Vietnamese dependency parsing. in T Cohn (ed.), Australasian Language Technology Association Workshop 2016: proceedings of the workshop. Australasian Language Technology Association, Melbourne, Australia, pp. 143-149, Australasian Language Technology Association Workshop (14th : 2016), Caulfield, Australia, 5/12/16. <http://aclanthology.info/papers/an-empirical-study-for-vietnamese-dependency-parsing>

An empirical study for Vietnamese dependency parsing. / Nguyen, Dat Quoc; Dras, Mark ; Johnson, Mark.
Australasian Language Technology Association Workshop 2016: proceedings of the workshop. ed. / Trevor Cohn. Melbourne, Australia: Australasian Language Technology Association, 2016. p. 143-149.

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

TY - GEN

T1 - An empirical study for Vietnamese dependency parsing

AU - Nguyen, Dat Quoc

AU - Dras, Mark

AU - Johnson, Mark

PY - 2016/12/1

Y1 - 2016/12/1

N2 - This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.

AB - This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.

M3 - Conference proceeding contribution

SP - 143

EP - 149

BT - Australasian Language Technology Association Workshop 2016

A2 - Cohn, Trevor

PB - Australasian Language Technology Association

CY - Melbourne, Australia

T2 - Australasian Language Technology Association Workshop (14th : 2016)

Y2 - 5 December 2016 through 7 December 2016

ER -

An empirical study for Vietnamese dependency parsing

Abstract

Conference

Access to Document

Fingerprint

Cite this