@inproceedings{sagot-boullier-2006-deep,
title = "Deep non-probabilistic parsing of large corpora",
author = "Sagot, Beno{\^\i}t and
Boullier, Pierre",
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/806_pdf.pdf",
abstract = "This paper reports a large-scale non-probabilistic parsing experiment with a deep LFG parser. We briefly introduce the parser we used, named SXLFG, and the resources that were used together with it. Then we report quantitative results about the parsing of a multi-million word journalistic corpus. We show that we can parse more than 6 million words in less than 12 hours, only 6.7{\%} of all sentences reaching the 1s timeout. This shows that deep large-coverage non-probabilistic parsers can be efficient enough to parse very large corpora in a reasonable amount of time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sagot-boullier-2006-deep">
<titleInfo>
<title>Deep non-probabilistic parsing of large corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Boullier</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>This paper reports a large-scale non-probabilistic parsing experiment with a deep LFG parser. We briefly introduce the parser we used, named SXLFG, and the resources that were used together with it. Then we report quantitative results about the parsing of a multi-million word journalistic corpus. We show that we can parse more than 6 million words in less than 12 hours, only 6.7% of all sentences reaching the 1s timeout. This shows that deep large-coverage non-probabilistic parsers can be efficient enough to parse very large corpora in a reasonable amount of time.</abstract>
<identifier type="citekey">sagot-boullier-2006-deep</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/806_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep non-probabilistic parsing of large corpora
%A Sagot, Benoît
%A Boullier, Pierre
%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 sagot-boullier-2006-deep
%X This paper reports a large-scale non-probabilistic parsing experiment with a deep LFG parser. We briefly introduce the parser we used, named SXLFG, and the resources that were used together with it. Then we report quantitative results about the parsing of a multi-million word journalistic corpus. We show that we can parse more than 6 million words in less than 12 hours, only 6.7% of all sentences reaching the 1s timeout. This shows that deep large-coverage non-probabilistic parsers can be efficient enough to parse very large corpora in a reasonable amount of time.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/806_pdf.pdf
Markdown (Informal)
[Deep non-probabilistic parsing of large corpora](http://www.lrec-conf.org/proceedings/lrec2006/pdf/806_pdf.pdf) (Sagot & Boullier, LREC 2006)
ACL
- Benoît Sagot and Pierre Boullier. 2006. Deep non-probabilistic parsing of large corpora. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).