@inproceedings{by-2008-kalshnikov,
title = "The Kalshnikov 691 Dependency Bank",
author = "By, Tomas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/176_paper.pdf",
abstract = "The PARC 700 dependency bank has a number of features that would seem to make it less than optimally suited for its intended purpose, parser evaluation. However, it is difficult to know precisely what impact these problems have on the evaluation results, and as a first step towards making comparison possible, a subset of the same sentences is presented here, marked up using a different format that avoids them. In this new representation, the tokens contain exactly the same sequence of characters as the original text, word order is encoded explicitly, and there is no artificial distinction between full tokens and attribute tokens. There is also a clear division between word tokens and empty nodes, and the token attributes are stored together with the word, instead of being spread out individually in the file. A standard programming language syntax is used for the data, so there is little room for markup errors. Finally, the dependency links are closer to standard grammatical terms, which presumably makes it easier to understand what they mean and to convert any particular parser output format to the Kalashnikov 691 representation. The data is provided both in machine-readable format and as graphical dependency trees.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="by-2008-kalshnikov">
<titleInfo>
<title>The Kalshnikov 691 Dependency Bank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomas</namePart>
<namePart type="family">By</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The PARC 700 dependency bank has a number of features that would seem to make it less than optimally suited for its intended purpose, parser evaluation. However, it is difficult to know precisely what impact these problems have on the evaluation results, and as a first step towards making comparison possible, a subset of the same sentences is presented here, marked up using a different format that avoids them. In this new representation, the tokens contain exactly the same sequence of characters as the original text, word order is encoded explicitly, and there is no artificial distinction between full tokens and attribute tokens. There is also a clear division between word tokens and empty nodes, and the token attributes are stored together with the word, instead of being spread out individually in the file. A standard programming language syntax is used for the data, so there is little room for markup errors. Finally, the dependency links are closer to standard grammatical terms, which presumably makes it easier to understand what they mean and to convert any particular parser output format to the Kalashnikov 691 representation. The data is provided both in machine-readable format and as graphical dependency trees.</abstract>
<identifier type="citekey">by-2008-kalshnikov</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/176_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Kalshnikov 691 Dependency Bank
%A By, Tomas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F by-2008-kalshnikov
%X The PARC 700 dependency bank has a number of features that would seem to make it less than optimally suited for its intended purpose, parser evaluation. However, it is difficult to know precisely what impact these problems have on the evaluation results, and as a first step towards making comparison possible, a subset of the same sentences is presented here, marked up using a different format that avoids them. In this new representation, the tokens contain exactly the same sequence of characters as the original text, word order is encoded explicitly, and there is no artificial distinction between full tokens and attribute tokens. There is also a clear division between word tokens and empty nodes, and the token attributes are stored together with the word, instead of being spread out individually in the file. A standard programming language syntax is used for the data, so there is little room for markup errors. Finally, the dependency links are closer to standard grammatical terms, which presumably makes it easier to understand what they mean and to convert any particular parser output format to the Kalashnikov 691 representation. The data is provided both in machine-readable format and as graphical dependency trees.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/176_paper.pdf
Markdown (Informal)
[The Kalshnikov 691 Dependency Bank](http://www.lrec-conf.org/proceedings/lrec2008/pdf/176_paper.pdf) (By, LREC 2008)
ACL
- Tomas By. 2008. The Kalshnikov 691 Dependency Bank. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).