@inproceedings{hanig-etal-2008-unsuparse,
title = "{U}nsu{P}arse: unsupervised Parsing with unsupervised Part of Speech Tagging",
author = {H{\"a}nig, Christian and
Bordag, Stefan and
Quasthoff, Uwe},
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/286_paper.pdf",
abstract = "Based on simple methods such as observing word and part of speech tag co-occurrence and clustering, we generate syntactic parses of sentences in an entirely unsupervised and self-inducing manner. The parser learns the structure of the language in question based on measuring breaking points within sentences. The learning process is divided into two phases, learning and application of learned knowledge. The basic learning works in an iterative manner which results in a hierarchical constituent representation of the sentence. Part-of-Speech tags are used to circumvent the data sparseness problem for rare words. The algorithm is applied on untagged data, on manually assigned tags and on tags produced by an unsupervised part of speech tagger. The results are unsurpassed by any self-induced parser and challenge the quality of trained parsers with respect to finding certain structures such as noun phrases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanig-etal-2008-unsuparse">
<titleInfo>
<title>UnsuParse: unsupervised Parsing with unsupervised Part of Speech Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hänig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Bordag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Quasthoff</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>Based on simple methods such as observing word and part of speech tag co-occurrence and clustering, we generate syntactic parses of sentences in an entirely unsupervised and self-inducing manner. The parser learns the structure of the language in question based on measuring breaking points within sentences. The learning process is divided into two phases, learning and application of learned knowledge. The basic learning works in an iterative manner which results in a hierarchical constituent representation of the sentence. Part-of-Speech tags are used to circumvent the data sparseness problem for rare words. The algorithm is applied on untagged data, on manually assigned tags and on tags produced by an unsupervised part of speech tagger. The results are unsurpassed by any self-induced parser and challenge the quality of trained parsers with respect to finding certain structures such as noun phrases.</abstract>
<identifier type="citekey">hanig-etal-2008-unsuparse</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/286_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnsuParse: unsupervised Parsing with unsupervised Part of Speech Tagging
%A Hänig, Christian
%A Bordag, Stefan
%A Quasthoff, Uwe
%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 hanig-etal-2008-unsuparse
%X Based on simple methods such as observing word and part of speech tag co-occurrence and clustering, we generate syntactic parses of sentences in an entirely unsupervised and self-inducing manner. The parser learns the structure of the language in question based on measuring breaking points within sentences. The learning process is divided into two phases, learning and application of learned knowledge. The basic learning works in an iterative manner which results in a hierarchical constituent representation of the sentence. Part-of-Speech tags are used to circumvent the data sparseness problem for rare words. The algorithm is applied on untagged data, on manually assigned tags and on tags produced by an unsupervised part of speech tagger. The results are unsurpassed by any self-induced parser and challenge the quality of trained parsers with respect to finding certain structures such as noun phrases.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/286_paper.pdf
Markdown (Informal)
[UnsuParse: unsupervised Parsing with unsupervised Part of Speech Tagging](http://www.lrec-conf.org/proceedings/lrec2008/pdf/286_paper.pdf) (Hänig et al., LREC 2008)
ACL