@inproceedings{mihaila-etal-2010-romanian,
title = "{R}omanian Zero Pronoun Distribution: A Comparative Study",
author = "Mih{\u{a}}il{\u{a}}, Claudiu and
Ilisei, Iustina and
Inkpen, Diana",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/851_Paper.pdf",
abstract = "Anaphora resolution is still a challenging research field in natural language processing, lacking a algorithm that correctly resolves anaphoric pronouns. Anaphoric zero pronouns pose an even greater challenge, since this category is not lexically realised. Thus, their resolution is conditioned by their prior identification stage. This paper reports on the distribution of zero pronouns in Romanian in various genres: encyclopaedic, legal, literary, and news-wire texts. For this purpose, the RoZP corpus has been created, containing almost 50000 tokens and 800 zero pronouns which are manually annotated. The distribution patterns are compared across genres, and exceptional cases are presented in order to facilitate the methodological process of developing a future zero pronoun identification and resolution algorithm. The evaluation results emphasise that zero pronouns appear frequently in Romanian, and their distribution depends largely on the genre. Additionally, possible features are revealed for their identification, and a search scope for the antecedent has been determined, increasing the chances of correct resolution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mihaila-etal-2010-romanian">
<titleInfo>
<title>Romanian Zero Pronoun Distribution: A Comparative Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claudiu</namePart>
<namePart type="family">Mihăilă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iustina</namePart>
<namePart type="family">Ilisei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Inkpen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Anaphora resolution is still a challenging research field in natural language processing, lacking a algorithm that correctly resolves anaphoric pronouns. Anaphoric zero pronouns pose an even greater challenge, since this category is not lexically realised. Thus, their resolution is conditioned by their prior identification stage. This paper reports on the distribution of zero pronouns in Romanian in various genres: encyclopaedic, legal, literary, and news-wire texts. For this purpose, the RoZP corpus has been created, containing almost 50000 tokens and 800 zero pronouns which are manually annotated. The distribution patterns are compared across genres, and exceptional cases are presented in order to facilitate the methodological process of developing a future zero pronoun identification and resolution algorithm. The evaluation results emphasise that zero pronouns appear frequently in Romanian, and their distribution depends largely on the genre. Additionally, possible features are revealed for their identification, and a search scope for the antecedent has been determined, increasing the chances of correct resolution.</abstract>
<identifier type="citekey">mihaila-etal-2010-romanian</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/851_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Romanian Zero Pronoun Distribution: A Comparative Study
%A Mihăilă, Claudiu
%A Ilisei, Iustina
%A Inkpen, Diana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F mihaila-etal-2010-romanian
%X Anaphora resolution is still a challenging research field in natural language processing, lacking a algorithm that correctly resolves anaphoric pronouns. Anaphoric zero pronouns pose an even greater challenge, since this category is not lexically realised. Thus, their resolution is conditioned by their prior identification stage. This paper reports on the distribution of zero pronouns in Romanian in various genres: encyclopaedic, legal, literary, and news-wire texts. For this purpose, the RoZP corpus has been created, containing almost 50000 tokens and 800 zero pronouns which are manually annotated. The distribution patterns are compared across genres, and exceptional cases are presented in order to facilitate the methodological process of developing a future zero pronoun identification and resolution algorithm. The evaluation results emphasise that zero pronouns appear frequently in Romanian, and their distribution depends largely on the genre. Additionally, possible features are revealed for their identification, and a search scope for the antecedent has been determined, increasing the chances of correct resolution.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/851_Paper.pdf
Markdown (Informal)
[Romanian Zero Pronoun Distribution: A Comparative Study](http://www.lrec-conf.org/proceedings/lrec2010/pdf/851_Paper.pdf) (Mihăilă et al., LREC 2010)
ACL
- Claudiu Mihăilă, Iustina Ilisei, and Diana Inkpen. 2010. Romanian Zero Pronoun Distribution: A Comparative Study. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).