@inproceedings{muhonen-purtonen-2012-rule,
title = "Rule-Based Detection of Clausal Coordinate Ellipsis",
author = "Muhonen, Kristiina and
Purtonen, Tanja",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/313_Paper.pdf",
pages = "1955--1959",
abstract = "With our experiment, we show how we can detect and annotate clausal coordinate ellipsis with Constraint Grammar rules. We focus on such an elliptical structure in which there are two coordinated clauses, and the latter one lacks a verb. For example, the sentence This belongs to me and that to you demonstrates the ellipsis in question, namely gapping. The Constraint Grammar rules are made for a Finnish parsebank, FinnTreeBank. The FinnTreeBank project is building a parsebank in the dependency syntactic framework in which verbs are central since other sentence elements depend on them. Without correct detection of omitted verbs, the syntactic analysis of the whole sentence fails. In the experiment, we detect gapping based on morphology and linear order of the words without using syntactic or semantic information. The test corpus, Finnish Wikipedia, is morphologically analyzed but not disambiguated. Even with an ambiguous morphological analysis, the results show that 89,9{\%} of the detected sentences are elliptical, making the rules accurate enough to be used in the creation of FinnTreeBank. Once we have a morphologically disambiguated corpus, we can write more accurate rules and expect better results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muhonen-purtonen-2012-rule">
<titleInfo>
<title>Rule-Based Detection of Clausal Coordinate Ellipsis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristiina</namePart>
<namePart type="family">Muhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Purtonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With our experiment, we show how we can detect and annotate clausal coordinate ellipsis with Constraint Grammar rules. We focus on such an elliptical structure in which there are two coordinated clauses, and the latter one lacks a verb. For example, the sentence This belongs to me and that to you demonstrates the ellipsis in question, namely gapping. The Constraint Grammar rules are made for a Finnish parsebank, FinnTreeBank. The FinnTreeBank project is building a parsebank in the dependency syntactic framework in which verbs are central since other sentence elements depend on them. Without correct detection of omitted verbs, the syntactic analysis of the whole sentence fails. In the experiment, we detect gapping based on morphology and linear order of the words without using syntactic or semantic information. The test corpus, Finnish Wikipedia, is morphologically analyzed but not disambiguated. Even with an ambiguous morphological analysis, the results show that 89,9% of the detected sentences are elliptical, making the rules accurate enough to be used in the creation of FinnTreeBank. Once we have a morphologically disambiguated corpus, we can write more accurate rules and expect better results.</abstract>
<identifier type="citekey">muhonen-purtonen-2012-rule</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/313_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1955</start>
<end>1959</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rule-Based Detection of Clausal Coordinate Ellipsis
%A Muhonen, Kristiina
%A Purtonen, Tanja
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F muhonen-purtonen-2012-rule
%X With our experiment, we show how we can detect and annotate clausal coordinate ellipsis with Constraint Grammar rules. We focus on such an elliptical structure in which there are two coordinated clauses, and the latter one lacks a verb. For example, the sentence This belongs to me and that to you demonstrates the ellipsis in question, namely gapping. The Constraint Grammar rules are made for a Finnish parsebank, FinnTreeBank. The FinnTreeBank project is building a parsebank in the dependency syntactic framework in which verbs are central since other sentence elements depend on them. Without correct detection of omitted verbs, the syntactic analysis of the whole sentence fails. In the experiment, we detect gapping based on morphology and linear order of the words without using syntactic or semantic information. The test corpus, Finnish Wikipedia, is morphologically analyzed but not disambiguated. Even with an ambiguous morphological analysis, the results show that 89,9% of the detected sentences are elliptical, making the rules accurate enough to be used in the creation of FinnTreeBank. Once we have a morphologically disambiguated corpus, we can write more accurate rules and expect better results.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/313_Paper.pdf
%P 1955-1959
Markdown (Informal)
[Rule-Based Detection of Clausal Coordinate Ellipsis](http://www.lrec-conf.org/proceedings/lrec2012/pdf/313_Paper.pdf) (Muhonen & Purtonen, LREC 2012)
ACL
- Kristiina Muhonen and Tanja Purtonen. 2012. Rule-Based Detection of Clausal Coordinate Ellipsis. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1955–1959, Istanbul, Turkey. European Language Resources Association (ELRA).