@inproceedings{morgado-da-costa-etal-2022-tembusu,
title = "The Tembusu Treebank: An {E}nglish Learner Treebank",
author = "Morgado da Costa, Lu{\'i}s and
Bond, Francis and
Winder, Roger V. P.",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.515/",
pages = "4817--4826",
abstract = "This paper reports on the creation and development of the Tembusu Learner Treebank {---} an open treebank created from the NTU Corpus of Learner English, unique for incorporating mal-rules in the annotation of ungrammatical sentences. It describes the motivation and development of the treebank, as well as its exploitation to build a new parse-ranking model for the English Resource Grammar, designed to help improve the parse selection of ungrammatical sentences and diagnose these sentences through mal-rules. The corpus contains 25,000 sentences, of which 4,900 are treebanked. The paper concludes with an evaluation experiment that shows the usefulness of this new treebank in the tasks of grammatical error detection and diagnosis."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morgado-da-costa-etal-2022-tembusu">
<titleInfo>
<title>The Tembusu Treebank: An English Learner Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Morgado da Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="given">V</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Winder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports on the creation and development of the Tembusu Learner Treebank — an open treebank created from the NTU Corpus of Learner English, unique for incorporating mal-rules in the annotation of ungrammatical sentences. It describes the motivation and development of the treebank, as well as its exploitation to build a new parse-ranking model for the English Resource Grammar, designed to help improve the parse selection of ungrammatical sentences and diagnose these sentences through mal-rules. The corpus contains 25,000 sentences, of which 4,900 are treebanked. The paper concludes with an evaluation experiment that shows the usefulness of this new treebank in the tasks of grammatical error detection and diagnosis.</abstract>
<identifier type="citekey">morgado-da-costa-etal-2022-tembusu</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.515/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4817</start>
<end>4826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Tembusu Treebank: An English Learner Treebank
%A Morgado da Costa, Luís
%A Bond, Francis
%A Winder, Roger V. P.
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F morgado-da-costa-etal-2022-tembusu
%X This paper reports on the creation and development of the Tembusu Learner Treebank — an open treebank created from the NTU Corpus of Learner English, unique for incorporating mal-rules in the annotation of ungrammatical sentences. It describes the motivation and development of the treebank, as well as its exploitation to build a new parse-ranking model for the English Resource Grammar, designed to help improve the parse selection of ungrammatical sentences and diagnose these sentences through mal-rules. The corpus contains 25,000 sentences, of which 4,900 are treebanked. The paper concludes with an evaluation experiment that shows the usefulness of this new treebank in the tasks of grammatical error detection and diagnosis.
%U https://aclanthology.org/2022.lrec-1.515/
%P 4817-4826
Markdown (Informal)
[The Tembusu Treebank: An English Learner Treebank](https://aclanthology.org/2022.lrec-1.515/) (Morgado da Costa et al., LREC 2022)
ACL
- Luís Morgado da Costa, Francis Bond, and Roger V. P. Winder. 2022. The Tembusu Treebank: An English Learner Treebank. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4817–4826, Marseille, France. European Language Resources Association.