@inproceedings{osenova-etal-2022-bulgarian,
title = "The {B}ulgarian Event Corpus: Overview and Initial {NER} Experiments",
author = "Osenova, Petya and
Simov, Kiril and
Marinova, Iva and
Berbatova, Melania",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.374",
pages = "3491--3499",
abstract = "The paper describes the Bulgarian Event Corpus (BEC). The annotation scheme is based on CIDOC-CRM ontology and on the English Framenet, adjusted for our task. It includes two main layers: named entities and events with their roles. The corpus is multi-domain and mainly oriented towards Social Sciences and Humanities (SSH). It will be used for: extracting knowledge and making it available through the Bulgaria-centric Knowledge Graph; further developing an annotation scheme that handles multiple domains in SSH; training automatic modules for the most important knowledge-based tasks, such as domain-specific and nested NER, NEL, event detection and profiling. Initial experiments were conducted on standard NER task due to complexity of the dataset and the rich NE annotation scheme. The results are promising with respect to some labels and give insights on handling better other ones. These experiments serve also as error detection modules that would help us in scheme re-design. They are a basis for further and more complex tasks, such as nested NER, NEL and event detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="osenova-etal-2022-bulgarian">
<titleInfo>
<title>The Bulgarian Event Corpus: Overview and Initial NER Experiments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiril</namePart>
<namePart type="family">Simov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iva</namePart>
<namePart type="family">Marinova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melania</namePart>
<namePart type="family">Berbatova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper describes the Bulgarian Event Corpus (BEC). The annotation scheme is based on CIDOC-CRM ontology and on the English Framenet, adjusted for our task. It includes two main layers: named entities and events with their roles. The corpus is multi-domain and mainly oriented towards Social Sciences and Humanities (SSH). It will be used for: extracting knowledge and making it available through the Bulgaria-centric Knowledge Graph; further developing an annotation scheme that handles multiple domains in SSH; training automatic modules for the most important knowledge-based tasks, such as domain-specific and nested NER, NEL, event detection and profiling. Initial experiments were conducted on standard NER task due to complexity of the dataset and the rich NE annotation scheme. The results are promising with respect to some labels and give insights on handling better other ones. These experiments serve also as error detection modules that would help us in scheme re-design. They are a basis for further and more complex tasks, such as nested NER, NEL and event detection.</abstract>
<identifier type="citekey">osenova-etal-2022-bulgarian</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.374</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3491</start>
<end>3499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Bulgarian Event Corpus: Overview and Initial NER Experiments
%A Osenova, Petya
%A Simov, Kiril
%A Marinova, Iva
%A Berbatova, Melania
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F osenova-etal-2022-bulgarian
%X The paper describes the Bulgarian Event Corpus (BEC). The annotation scheme is based on CIDOC-CRM ontology and on the English Framenet, adjusted for our task. It includes two main layers: named entities and events with their roles. The corpus is multi-domain and mainly oriented towards Social Sciences and Humanities (SSH). It will be used for: extracting knowledge and making it available through the Bulgaria-centric Knowledge Graph; further developing an annotation scheme that handles multiple domains in SSH; training automatic modules for the most important knowledge-based tasks, such as domain-specific and nested NER, NEL, event detection and profiling. Initial experiments were conducted on standard NER task due to complexity of the dataset and the rich NE annotation scheme. The results are promising with respect to some labels and give insights on handling better other ones. These experiments serve also as error detection modules that would help us in scheme re-design. They are a basis for further and more complex tasks, such as nested NER, NEL and event detection.
%U https://aclanthology.org/2022.lrec-1.374
%P 3491-3499
Markdown (Informal)
[The Bulgarian Event Corpus: Overview and Initial NER Experiments](https://aclanthology.org/2022.lrec-1.374) (Osenova et al., LREC 2022)
ACL