@inproceedings{pilan-etal-2016-predicting,
title = "Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks",
author = "Pil{\'a}n, Ildik{\'o} and
Volodina, Elena and
Zesch, Torsten",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1198",
pages = "2101--2111",
abstract = "The lack of a sufficient amount of data tailored for a task is a well-recognized problem for many statistical NLP methods. In this paper, we explore whether data sparsity can be successfully tackled when classifying language proficiency levels in the domain of learner-written output texts. We aim at overcoming data sparsity by incorporating knowledge in the trained model from another domain consisting of input texts written by teaching professionals for learners. We compare different domain adaptation techniques and find that a weighted combination of the two types of data performs best, which can even rival systems based on considerably larger amounts of in-domain data. Moreover, we show that normalizing errors in learners{'} texts can substantially improve classification when level-annotated in-domain data is not available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pilan-etal-2016-predicting">
<titleInfo>
<title>Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The lack of a sufficient amount of data tailored for a task is a well-recognized problem for many statistical NLP methods. In this paper, we explore whether data sparsity can be successfully tackled when classifying language proficiency levels in the domain of learner-written output texts. We aim at overcoming data sparsity by incorporating knowledge in the trained model from another domain consisting of input texts written by teaching professionals for learners. We compare different domain adaptation techniques and find that a weighted combination of the two types of data performs best, which can even rival systems based on considerably larger amounts of in-domain data. Moreover, we show that normalizing errors in learners’ texts can substantially improve classification when level-annotated in-domain data is not available.</abstract>
<identifier type="citekey">pilan-etal-2016-predicting</identifier>
<location>
<url>https://aclanthology.org/C16-1198</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>2101</start>
<end>2111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks
%A Pilán, Ildikó
%A Volodina, Elena
%A Zesch, Torsten
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F pilan-etal-2016-predicting
%X The lack of a sufficient amount of data tailored for a task is a well-recognized problem for many statistical NLP methods. In this paper, we explore whether data sparsity can be successfully tackled when classifying language proficiency levels in the domain of learner-written output texts. We aim at overcoming data sparsity by incorporating knowledge in the trained model from another domain consisting of input texts written by teaching professionals for learners. We compare different domain adaptation techniques and find that a weighted combination of the two types of data performs best, which can even rival systems based on considerably larger amounts of in-domain data. Moreover, we show that normalizing errors in learners’ texts can substantially improve classification when level-annotated in-domain data is not available.
%U https://aclanthology.org/C16-1198
%P 2101-2111
Markdown (Informal)
[Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks](https://aclanthology.org/C16-1198) (Pilán et al., COLING 2016)
ACL