@inproceedings{ghayoomi-2012-grammar,
title = "From Grammar Rule Extraction to Treebanking: A Bootstrapping Approach",
author = "Ghayoomi, Masood",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/900_Paper.pdf",
pages = "1912--1919",
abstract = "Most of the reliable language resources are developed via human supervision. Developing supervised annotated data is hard and tedious, and it will be very time consuming when it is done totally manually; as a result, various types of annotated data, including treebanks, are not available for many languages. Considering that a portion of the language is regular, we can define regular expressions as grammar rules to recognize the strings which match the regular expressions, and reduce the human effort to annotate further unseen data. In this paper, we propose an incremental bootstrapping approach via extracting grammar rules when no treebank is available in the first step. Since Persian suffers from lack of available data sources, we have applied our method to develop a treebank for this language. Our experiment shows that this approach significantly decreases the amount of manual effort in the annotation process while enlarging the treebank.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghayoomi-2012-grammar">
<titleInfo>
<title>From Grammar Rule Extraction to Treebanking: A Bootstrapping Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masood</namePart>
<namePart type="family">Ghayoomi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most of the reliable language resources are developed via human supervision. Developing supervised annotated data is hard and tedious, and it will be very time consuming when it is done totally manually; as a result, various types of annotated data, including treebanks, are not available for many languages. Considering that a portion of the language is regular, we can define regular expressions as grammar rules to recognize the strings which match the regular expressions, and reduce the human effort to annotate further unseen data. In this paper, we propose an incremental bootstrapping approach via extracting grammar rules when no treebank is available in the first step. Since Persian suffers from lack of available data sources, we have applied our method to develop a treebank for this language. Our experiment shows that this approach significantly decreases the amount of manual effort in the annotation process while enlarging the treebank.</abstract>
<identifier type="citekey">ghayoomi-2012-grammar</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/900_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1912</start>
<end>1919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Grammar Rule Extraction to Treebanking: A Bootstrapping Approach
%A Ghayoomi, Masood
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F ghayoomi-2012-grammar
%X Most of the reliable language resources are developed via human supervision. Developing supervised annotated data is hard and tedious, and it will be very time consuming when it is done totally manually; as a result, various types of annotated data, including treebanks, are not available for many languages. Considering that a portion of the language is regular, we can define regular expressions as grammar rules to recognize the strings which match the regular expressions, and reduce the human effort to annotate further unseen data. In this paper, we propose an incremental bootstrapping approach via extracting grammar rules when no treebank is available in the first step. Since Persian suffers from lack of available data sources, we have applied our method to develop a treebank for this language. Our experiment shows that this approach significantly decreases the amount of manual effort in the annotation process while enlarging the treebank.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/900_Paper.pdf
%P 1912-1919
Markdown (Informal)
[From Grammar Rule Extraction to Treebanking: A Bootstrapping Approach](http://www.lrec-conf.org/proceedings/lrec2012/pdf/900_Paper.pdf) (Ghayoomi, LREC 2012)
ACL