@inproceedings{morales-etal-2016-hypergraph,
title = "Hypergraph Modelization of a Syntactically Annotated {E}nglish {W}ikipedia Dump",
author = "Morales, Edmundo Pavel Soriano and
Ah-Pine, Julien and
Loudcher, Sabine",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1372",
pages = "2348--2353",
abstract = "Wikipedia, the well known internet encyclopedia, is nowadays a widely used source of information. To leverage its rich information, already parsed versions of Wikipedia have been proposed. We present an annotated dump of the English Wikipedia. This dump draws upon previously released Wikipedia parsed dumps. Still, we head in a different direction. In this parse we focus more into the syntactical characteristics of words: aside from the classical Part-of-Speech (PoS) tags and dependency parsing relations, we provide the full constituent parse branch for each word in a succinct way. Additionally, we propose a hypergraph network representation of the extracted linguistic information. The proposed modelization aims to take advantage of the information stocked within our parsed Wikipedia dump. We hope that by releasing these resources, researchers from the concerned communities will have a ready-to-experiment Wikipedia corpus to compare and distribute their work. We render public our parsed Wikipedia dump as well as the tool (and its source code) used to perform the parse. The hypergraph network and its related metadata is also distributed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morales-etal-2016-hypergraph">
<titleInfo>
<title>Hypergraph Modelization of a Syntactically Annotated English Wikipedia Dump</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edmundo</namePart>
<namePart type="given">Pavel</namePart>
<namePart type="given">Soriano</namePart>
<namePart type="family">Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Ah-Pine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Loudcher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Wikipedia, the well known internet encyclopedia, is nowadays a widely used source of information. To leverage its rich information, already parsed versions of Wikipedia have been proposed. We present an annotated dump of the English Wikipedia. This dump draws upon previously released Wikipedia parsed dumps. Still, we head in a different direction. In this parse we focus more into the syntactical characteristics of words: aside from the classical Part-of-Speech (PoS) tags and dependency parsing relations, we provide the full constituent parse branch for each word in a succinct way. Additionally, we propose a hypergraph network representation of the extracted linguistic information. The proposed modelization aims to take advantage of the information stocked within our parsed Wikipedia dump. We hope that by releasing these resources, researchers from the concerned communities will have a ready-to-experiment Wikipedia corpus to compare and distribute their work. We render public our parsed Wikipedia dump as well as the tool (and its source code) used to perform the parse. The hypergraph network and its related metadata is also distributed.</abstract>
<identifier type="citekey">morales-etal-2016-hypergraph</identifier>
<location>
<url>https://aclanthology.org/L16-1372</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2348</start>
<end>2353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hypergraph Modelization of a Syntactically Annotated English Wikipedia Dump
%A Morales, Edmundo Pavel Soriano
%A Ah-Pine, Julien
%A Loudcher, Sabine
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F morales-etal-2016-hypergraph
%X Wikipedia, the well known internet encyclopedia, is nowadays a widely used source of information. To leverage its rich information, already parsed versions of Wikipedia have been proposed. We present an annotated dump of the English Wikipedia. This dump draws upon previously released Wikipedia parsed dumps. Still, we head in a different direction. In this parse we focus more into the syntactical characteristics of words: aside from the classical Part-of-Speech (PoS) tags and dependency parsing relations, we provide the full constituent parse branch for each word in a succinct way. Additionally, we propose a hypergraph network representation of the extracted linguistic information. The proposed modelization aims to take advantage of the information stocked within our parsed Wikipedia dump. We hope that by releasing these resources, researchers from the concerned communities will have a ready-to-experiment Wikipedia corpus to compare and distribute their work. We render public our parsed Wikipedia dump as well as the tool (and its source code) used to perform the parse. The hypergraph network and its related metadata is also distributed.
%U https://aclanthology.org/L16-1372
%P 2348-2353
Markdown (Informal)
[Hypergraph Modelization of a Syntactically Annotated English Wikipedia Dump](https://aclanthology.org/L16-1372) (Morales et al., LREC 2016)
ACL