@inproceedings{novak-hajic-2006-perspectives,
title = "Perspectives of Turning {P}rague Dependency Treebank into a Knowledge Base",
author = "Nov{\'a}k, V{\'a}clav and
Haji{\v{c}}, Jan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/245_pdf.pdf",
abstract = "Recently, the Prague Dependency Treebank 2.0 (PDT 2.0) has emerged as the largest text corpora annotated on the level of tectogrammatical representation (linguistic meaning) described in Sgall et al. (2004) and containing about 0.8 milion words (see Hajic (2004)). We hope that this level of annotation is so close to the meaning of the utterances contained in the corpora that it should enable us to automatically transform texts contained in the corpora to the form of knowledge base, usable for information extraction, question answering, summarization, etc. We can use Multilayered Extended Semantic Networks (MultiNet) described in Helbig (2006) as the target formalism. In this paper we discuss the suitability of such approach and some of the main issues that will arise in the process. In section 1, we introduce formalisms underlying PDT 2.0 and MultiNet, in section 2. We describe the role MultiNet can play in the system of Functional Generative Description (FGD), section 3 discusses issues of automatic conversion to MultiNet and section 4 gives some conclusions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="novak-hajic-2006-perspectives">
<titleInfo>
<title>Perspectives of Turning Prague Dependency Treebank into a Knowledge Base</title>
</titleInfo>
<name type="personal">
<namePart type="given">Václav</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hajič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, the Prague Dependency Treebank 2.0 (PDT 2.0) has emerged as the largest text corpora annotated on the level of tectogrammatical representation (linguistic meaning) described in Sgall et al. (2004) and containing about 0.8 milion words (see Hajic (2004)). We hope that this level of annotation is so close to the meaning of the utterances contained in the corpora that it should enable us to automatically transform texts contained in the corpora to the form of knowledge base, usable for information extraction, question answering, summarization, etc. We can use Multilayered Extended Semantic Networks (MultiNet) described in Helbig (2006) as the target formalism. In this paper we discuss the suitability of such approach and some of the main issues that will arise in the process. In section 1, we introduce formalisms underlying PDT 2.0 and MultiNet, in section 2. We describe the role MultiNet can play in the system of Functional Generative Description (FGD), section 3 discusses issues of automatic conversion to MultiNet and section 4 gives some conclusions.</abstract>
<identifier type="citekey">novak-hajic-2006-perspectives</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/245_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perspectives of Turning Prague Dependency Treebank into a Knowledge Base
%A Novák, Václav
%A Hajič, Jan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F novak-hajic-2006-perspectives
%X Recently, the Prague Dependency Treebank 2.0 (PDT 2.0) has emerged as the largest text corpora annotated on the level of tectogrammatical representation (linguistic meaning) described in Sgall et al. (2004) and containing about 0.8 milion words (see Hajic (2004)). We hope that this level of annotation is so close to the meaning of the utterances contained in the corpora that it should enable us to automatically transform texts contained in the corpora to the form of knowledge base, usable for information extraction, question answering, summarization, etc. We can use Multilayered Extended Semantic Networks (MultiNet) described in Helbig (2006) as the target formalism. In this paper we discuss the suitability of such approach and some of the main issues that will arise in the process. In section 1, we introduce formalisms underlying PDT 2.0 and MultiNet, in section 2. We describe the role MultiNet can play in the system of Functional Generative Description (FGD), section 3 discusses issues of automatic conversion to MultiNet and section 4 gives some conclusions.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/245_pdf.pdf
Markdown (Informal)
[Perspectives of Turning Prague Dependency Treebank into a Knowledge Base](http://www.lrec-conf.org/proceedings/lrec2006/pdf/245_pdf.pdf) (Novák & Hajič, LREC 2006)
ACL