@inproceedings{shiue-chen-2016-detecting,
title = "Detecting Word Usage Errors in {C}hinese Sentences for Learning {C}hinese as a Foreign Language",
author = "Shiue, Yow-Ting and
Chen, Hsin-Hsi",
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/L16-1033",
pages = "220--224",
abstract = "Automated grammatical error detection, which helps users improve their writing, is an important application in NLP. Recently more and more people are learning Chinese, and an automated error detection system can be helpful for the learners. This paper proposes n-gram features, dependency count features, dependency bigram features, and single-character features to determine if a Chinese sentence contains word usage errors, in which a word is written as a wrong form or the word selection is inappropriate. With marking potential errors on the level of sentence segments, typically delimited by punctuation marks, the learner can try to correct the problems without the assistant of a language teacher. Experiments on the HSK corpus show that the classifier combining all sets of features achieves an accuracy of 0.8423. By utilizing certain combination of the sets of features, we can construct a system that favors precision or recall. The best precision we achieve is 0.9536, indicating that our system is reliable and seldom produces misleading results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shiue-chen-2016-detecting">
<titleInfo>
<title>Detecting Word Usage Errors in Chinese Sentences for Learning Chinese as a Foreign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yow-Ting</namePart>
<namePart type="family">Shiue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</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>Automated grammatical error detection, which helps users improve their writing, is an important application in NLP. Recently more and more people are learning Chinese, and an automated error detection system can be helpful for the learners. This paper proposes n-gram features, dependency count features, dependency bigram features, and single-character features to determine if a Chinese sentence contains word usage errors, in which a word is written as a wrong form or the word selection is inappropriate. With marking potential errors on the level of sentence segments, typically delimited by punctuation marks, the learner can try to correct the problems without the assistant of a language teacher. Experiments on the HSK corpus show that the classifier combining all sets of features achieves an accuracy of 0.8423. By utilizing certain combination of the sets of features, we can construct a system that favors precision or recall. The best precision we achieve is 0.9536, indicating that our system is reliable and seldom produces misleading results.</abstract>
<identifier type="citekey">shiue-chen-2016-detecting</identifier>
<location>
<url>https://aclanthology.org/L16-1033</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>220</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Word Usage Errors in Chinese Sentences for Learning Chinese as a Foreign Language
%A Shiue, Yow-Ting
%A Chen, Hsin-Hsi
%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 shiue-chen-2016-detecting
%X Automated grammatical error detection, which helps users improve their writing, is an important application in NLP. Recently more and more people are learning Chinese, and an automated error detection system can be helpful for the learners. This paper proposes n-gram features, dependency count features, dependency bigram features, and single-character features to determine if a Chinese sentence contains word usage errors, in which a word is written as a wrong form or the word selection is inappropriate. With marking potential errors on the level of sentence segments, typically delimited by punctuation marks, the learner can try to correct the problems without the assistant of a language teacher. Experiments on the HSK corpus show that the classifier combining all sets of features achieves an accuracy of 0.8423. By utilizing certain combination of the sets of features, we can construct a system that favors precision or recall. The best precision we achieve is 0.9536, indicating that our system is reliable and seldom produces misleading results.
%U https://aclanthology.org/L16-1033
%P 220-224
Markdown (Informal)
[Detecting Word Usage Errors in Chinese Sentences for Learning Chinese as a Foreign Language](https://aclanthology.org/L16-1033) (Shiue & Chen, LREC 2016)
ACL