@inproceedings{giordani-moschitti-2010-corpora,
title = "Corpora for Automatically Learning to Map Natural Language Questions into {SQL} Queries",
author = "Giordani, Alessandra and
Moschitti, Alessandro",
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/724_Paper.pdf",
abstract = "Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem can be addressed by using machine learning algorithms to generate a function that find mappings between natural language and programming language semantics. For this purpose suitable annotated and structured data are required. In this paper, we describe our method to construct and semi-automatically annotate these kinds of data, consisting of pairs of NL questions and SQL queries. Additionally, we describe two different datasets obtained by applying our annotation method to two well-known corpora, GeoQueries and RestQueries. Since we believe that syntactic levels are important, we also generate and make available relational pairs represented by means of their syntactic trees whose lexical content has been generalized. We validate the quality of our corpora by experimenting with them and our machine learning models to derive automatic NL/SQL translators. Our promising results suggest that our corpora can be effectively used to carry out research in the field of natural language interface to database.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="giordani-moschitti-2010-corpora">
<titleInfo>
<title>Corpora for Automatically Learning to Map Natural Language Questions into SQL Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Giordani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</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>Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem can be addressed by using machine learning algorithms to generate a function that find mappings between natural language and programming language semantics. For this purpose suitable annotated and structured data are required. In this paper, we describe our method to construct and semi-automatically annotate these kinds of data, consisting of pairs of NL questions and SQL queries. Additionally, we describe two different datasets obtained by applying our annotation method to two well-known corpora, GeoQueries and RestQueries. Since we believe that syntactic levels are important, we also generate and make available relational pairs represented by means of their syntactic trees whose lexical content has been generalized. We validate the quality of our corpora by experimenting with them and our machine learning models to derive automatic NL/SQL translators. Our promising results suggest that our corpora can be effectively used to carry out research in the field of natural language interface to database.</abstract>
<identifier type="citekey">giordani-moschitti-2010-corpora</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/724_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpora for Automatically Learning to Map Natural Language Questions into SQL Queries
%A Giordani, Alessandra
%A Moschitti, Alessandro
%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 giordani-moschitti-2010-corpora
%X Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem can be addressed by using machine learning algorithms to generate a function that find mappings between natural language and programming language semantics. For this purpose suitable annotated and structured data are required. In this paper, we describe our method to construct and semi-automatically annotate these kinds of data, consisting of pairs of NL questions and SQL queries. Additionally, we describe two different datasets obtained by applying our annotation method to two well-known corpora, GeoQueries and RestQueries. Since we believe that syntactic levels are important, we also generate and make available relational pairs represented by means of their syntactic trees whose lexical content has been generalized. We validate the quality of our corpora by experimenting with them and our machine learning models to derive automatic NL/SQL translators. Our promising results suggest that our corpora can be effectively used to carry out research in the field of natural language interface to database.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/724_Paper.pdf
Markdown (Informal)
[Corpora for Automatically Learning to Map Natural Language Questions into SQL Queries](http://www.lrec-conf.org/proceedings/lrec2010/pdf/724_Paper.pdf) (Giordani & Moschitti, LREC 2010)
ACL