@inproceedings{kolachina-etal-2010-grammar,
title = "Grammar Extraction from Treebanks for {H}indi and {T}elugu",
author = "Kolachina, Prasanth and
Kolachina, Sudheer and
Singh, Anil Kumar and
Husain, Samar and
Naidu, Viswanath and
Sangal, Rajeev and
Bharati, Akshar",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/854_Paper.pdf",
abstract = "Grammars play an important role in many Natural Language Processing (NLP) applications. The traditional approach to creating grammars manually, besides being labor-intensive, has several limitations. With the availability of large scale syntactically annotated treebanks, it is now possible to automatically extract an approximate grammar of a language in any of the existing formalisms from a corresponding treebank. In this paper, we present a basic approach to extract grammars from dependency treebanks of two Indian languages, Hindi and Telugu. The process of grammar extraction requires a generalization mechanism. Towards this end, we explore an approach which relies on generalization of argument structure over the verbs based on their syntactic similarity. Such a generalization counters the effect of data sparseness in the treebanks. A grammar extracted using this system can not only expand already existing knowledge bases for NLP tasks such as parsing, but also aid in the creation of grammars for languages where none exist. Further, we show that the grammar extraction process can help in identifying annotation errors and thus aid in the task of the treebank validation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolachina-etal-2010-grammar">
<titleInfo>
<title>Grammar Extraction from Treebanks for Hindi and Telugu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prasanth</namePart>
<namePart type="family">Kolachina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudheer</namePart>
<namePart type="family">Kolachina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Husain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viswanath</namePart>
<namePart type="family">Naidu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshar</namePart>
<namePart type="family">Bharati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammars play an important role in many Natural Language Processing (NLP) applications. The traditional approach to creating grammars manually, besides being labor-intensive, has several limitations. With the availability of large scale syntactically annotated treebanks, it is now possible to automatically extract an approximate grammar of a language in any of the existing formalisms from a corresponding treebank. In this paper, we present a basic approach to extract grammars from dependency treebanks of two Indian languages, Hindi and Telugu. The process of grammar extraction requires a generalization mechanism. Towards this end, we explore an approach which relies on generalization of argument structure over the verbs based on their syntactic similarity. Such a generalization counters the effect of data sparseness in the treebanks. A grammar extracted using this system can not only expand already existing knowledge bases for NLP tasks such as parsing, but also aid in the creation of grammars for languages where none exist. Further, we show that the grammar extraction process can help in identifying annotation errors and thus aid in the task of the treebank validation.</abstract>
<identifier type="citekey">kolachina-etal-2010-grammar</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/854_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grammar Extraction from Treebanks for Hindi and Telugu
%A Kolachina, Prasanth
%A Kolachina, Sudheer
%A Singh, Anil Kumar
%A Husain, Samar
%A Naidu, Viswanath
%A Sangal, Rajeev
%A Bharati, Akshar
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F kolachina-etal-2010-grammar
%X Grammars play an important role in many Natural Language Processing (NLP) applications. The traditional approach to creating grammars manually, besides being labor-intensive, has several limitations. With the availability of large scale syntactically annotated treebanks, it is now possible to automatically extract an approximate grammar of a language in any of the existing formalisms from a corresponding treebank. In this paper, we present a basic approach to extract grammars from dependency treebanks of two Indian languages, Hindi and Telugu. The process of grammar extraction requires a generalization mechanism. Towards this end, we explore an approach which relies on generalization of argument structure over the verbs based on their syntactic similarity. Such a generalization counters the effect of data sparseness in the treebanks. A grammar extracted using this system can not only expand already existing knowledge bases for NLP tasks such as parsing, but also aid in the creation of grammars for languages where none exist. Further, we show that the grammar extraction process can help in identifying annotation errors and thus aid in the task of the treebank validation.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/854_Paper.pdf
Markdown (Informal)
[Grammar Extraction from Treebanks for Hindi and Telugu](http://www.lrec-conf.org/proceedings/lrec2010/pdf/854_Paper.pdf) (Kolachina et al., LREC 2010)
ACL
- Prasanth Kolachina, Sudheer Kolachina, Anil Kumar Singh, Samar Husain, Viswanath Naidu, Rajeev Sangal, and Akshar Bharati. 2010. Grammar Extraction from Treebanks for Hindi and Telugu. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).