@inproceedings{richardson-kuhn-2014-unixman,
title = "{U}nix{M}an Corpus: A Resource for Language Learning in the {U}nix Domain",
author = "Richardson, Kyle and
Kuhn, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/823_Paper.pdf",
pages = "2985--2989",
abstract = "We present a new resource, the UnixMan Corpus, for studying language learning it the domain of Unix utility manuals. The corpus is built by mining Unix (and other Unix related) man pages for parallel example entries, consisting of English textual descriptions with corresponding command examples. The commands provide a grounded and ambiguous semantics for the textual descriptions, making the corpus of interest to work on Semantic Parsing and Grounded Language Learning. In contrast to standard resources for Semantic Parsing, which tend to be restricted to a small number of concepts and relations, the UnixMan Corpus spans a wide variety of utility genres and topics, and consists of hundreds of command and domain entity types. The semi-structured nature of the manuals also makes it easy to exploit other types of relevant information for Grounded Language Learning. We describe the details of the corpus and provide preliminary classification results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="richardson-kuhn-2014-unixman">
<titleInfo>
<title>UnixMan Corpus: A Resource for Language Learning in the Unix Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new resource, the UnixMan Corpus, for studying language learning it the domain of Unix utility manuals. The corpus is built by mining Unix (and other Unix related) man pages for parallel example entries, consisting of English textual descriptions with corresponding command examples. The commands provide a grounded and ambiguous semantics for the textual descriptions, making the corpus of interest to work on Semantic Parsing and Grounded Language Learning. In contrast to standard resources for Semantic Parsing, which tend to be restricted to a small number of concepts and relations, the UnixMan Corpus spans a wide variety of utility genres and topics, and consists of hundreds of command and domain entity types. The semi-structured nature of the manuals also makes it easy to exploit other types of relevant information for Grounded Language Learning. We describe the details of the corpus and provide preliminary classification results.</abstract>
<identifier type="citekey">richardson-kuhn-2014-unixman</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/823_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2985</start>
<end>2989</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnixMan Corpus: A Resource for Language Learning in the Unix Domain
%A Richardson, Kyle
%A Kuhn, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F richardson-kuhn-2014-unixman
%X We present a new resource, the UnixMan Corpus, for studying language learning it the domain of Unix utility manuals. The corpus is built by mining Unix (and other Unix related) man pages for parallel example entries, consisting of English textual descriptions with corresponding command examples. The commands provide a grounded and ambiguous semantics for the textual descriptions, making the corpus of interest to work on Semantic Parsing and Grounded Language Learning. In contrast to standard resources for Semantic Parsing, which tend to be restricted to a small number of concepts and relations, the UnixMan Corpus spans a wide variety of utility genres and topics, and consists of hundreds of command and domain entity types. The semi-structured nature of the manuals also makes it easy to exploit other types of relevant information for Grounded Language Learning. We describe the details of the corpus and provide preliminary classification results.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/823_Paper.pdf
%P 2985-2989
Markdown (Informal)
[UnixMan Corpus: A Resource for Language Learning in the Unix Domain](http://www.lrec-conf.org/proceedings/lrec2014/pdf/823_Paper.pdf) (Richardson & Kuhn, LREC 2014)
ACL