@inproceedings{nguyen-etal-2016-challenges,
title = "Challenges and Solutions for Consistent Annotation of {V}ietnamese Treebank",
author = "Nguyen, Quy and
Miyao, Yusuke and
Le, Ha and
Nguyen, Ngan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1243/",
pages = "1532--1539",
abstract = "Treebanks are important resources for researchers in natural language processing, speech recognition, theoretical linguistics, etc. To strengthen the automatic processing of the Vietnamese language, a Vietnamese treebank has been built. However, the quality of this treebank is not satisfactory and is a possible source for the low performance of Vietnamese language processing. We have been building a new treebank for Vietnamese with about 40,000 sentences annotated with three layers: word segmentation, part-of-speech tagging, and bracketing. In this paper, we describe several challenges of Vietnamese language and how we solve them in developing annotation guidelines. We also present our methods to improve the quality of the annotation guidelines and ensure annotation accuracy and consistency. Experiment results show that inter-annotator agreement ratios and accuracy are higher than 90{\%} which is satisfactory."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2016-challenges">
<titleInfo>
<title>Challenges and Solutions for Consistent Annotation of Vietnamese Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quy</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ha</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Treebanks are important resources for researchers in natural language processing, speech recognition, theoretical linguistics, etc. To strengthen the automatic processing of the Vietnamese language, a Vietnamese treebank has been built. However, the quality of this treebank is not satisfactory and is a possible source for the low performance of Vietnamese language processing. We have been building a new treebank for Vietnamese with about 40,000 sentences annotated with three layers: word segmentation, part-of-speech tagging, and bracketing. In this paper, we describe several challenges of Vietnamese language and how we solve them in developing annotation guidelines. We also present our methods to improve the quality of the annotation guidelines and ensure annotation accuracy and consistency. Experiment results show that inter-annotator agreement ratios and accuracy are higher than 90% which is satisfactory.</abstract>
<identifier type="citekey">nguyen-etal-2016-challenges</identifier>
<location>
<url>https://aclanthology.org/L16-1243/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1532</start>
<end>1539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenges and Solutions for Consistent Annotation of Vietnamese Treebank
%A Nguyen, Quy
%A Miyao, Yusuke
%A Le, Ha
%A Nguyen, Ngan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F nguyen-etal-2016-challenges
%X Treebanks are important resources for researchers in natural language processing, speech recognition, theoretical linguistics, etc. To strengthen the automatic processing of the Vietnamese language, a Vietnamese treebank has been built. However, the quality of this treebank is not satisfactory and is a possible source for the low performance of Vietnamese language processing. We have been building a new treebank for Vietnamese with about 40,000 sentences annotated with three layers: word segmentation, part-of-speech tagging, and bracketing. In this paper, we describe several challenges of Vietnamese language and how we solve them in developing annotation guidelines. We also present our methods to improve the quality of the annotation guidelines and ensure annotation accuracy and consistency. Experiment results show that inter-annotator agreement ratios and accuracy are higher than 90% which is satisfactory.
%U https://aclanthology.org/L16-1243/
%P 1532-1539
Markdown (Informal)
[Challenges and Solutions for Consistent Annotation of Vietnamese Treebank](https://aclanthology.org/L16-1243/) (Nguyen et al., LREC 2016)
ACL