@inproceedings{koeva-etal-2020-natural,
title = "Natural Language Processing Pipeline to Annotate {B}ulgarian Legislative Documents",
author = "Koeva, Svetla and
Obreshkov, Nikola and
Yalamov, Martin",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.863",
pages = "6988--6994",
abstract = "The paper presents the Bulgarian MARCELL corpus, part of a recently developed multilingual corpus representing the national legislation in seven European countries and the NLP pipeline that turns the web crawled data into structured, linguistically annotated dataset. The Bulgarian data is web crawled, extracted from the original HTML format, filtered by document type, tokenised, sentence split, tagged and lemmatised with a fine-grained version of the Bulgarian Language Processing Chain, dependency parsed with NLP- Cube, annotated with named entities (persons, locations, organisations and others), noun phrases, IATE terms and EuroVoc descriptors. An orchestrator process has been developed to control the NLP pipeline performing an end-to-end data processing and annotation starting from the documents identification and ending in the generation of statistical reports. The Bulgarian MARCELL corpus consists of 25,283 documents (at the beginning of November 2019), which are classified into eleven types.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koeva-etal-2020-natural">
<titleInfo>
<title>Natural Language Processing Pipeline to Annotate Bulgarian Legislative Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Koeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Obreshkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Yalamov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The paper presents the Bulgarian MARCELL corpus, part of a recently developed multilingual corpus representing the national legislation in seven European countries and the NLP pipeline that turns the web crawled data into structured, linguistically annotated dataset. The Bulgarian data is web crawled, extracted from the original HTML format, filtered by document type, tokenised, sentence split, tagged and lemmatised with a fine-grained version of the Bulgarian Language Processing Chain, dependency parsed with NLP- Cube, annotated with named entities (persons, locations, organisations and others), noun phrases, IATE terms and EuroVoc descriptors. An orchestrator process has been developed to control the NLP pipeline performing an end-to-end data processing and annotation starting from the documents identification and ending in the generation of statistical reports. The Bulgarian MARCELL corpus consists of 25,283 documents (at the beginning of November 2019), which are classified into eleven types.</abstract>
<identifier type="citekey">koeva-etal-2020-natural</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.863</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6988</start>
<end>6994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Natural Language Processing Pipeline to Annotate Bulgarian Legislative Documents
%A Koeva, Svetla
%A Obreshkov, Nikola
%A Yalamov, Martin
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F koeva-etal-2020-natural
%X The paper presents the Bulgarian MARCELL corpus, part of a recently developed multilingual corpus representing the national legislation in seven European countries and the NLP pipeline that turns the web crawled data into structured, linguistically annotated dataset. The Bulgarian data is web crawled, extracted from the original HTML format, filtered by document type, tokenised, sentence split, tagged and lemmatised with a fine-grained version of the Bulgarian Language Processing Chain, dependency parsed with NLP- Cube, annotated with named entities (persons, locations, organisations and others), noun phrases, IATE terms and EuroVoc descriptors. An orchestrator process has been developed to control the NLP pipeline performing an end-to-end data processing and annotation starting from the documents identification and ending in the generation of statistical reports. The Bulgarian MARCELL corpus consists of 25,283 documents (at the beginning of November 2019), which are classified into eleven types.
%U https://aclanthology.org/2020.lrec-1.863
%P 6988-6994
Markdown (Informal)
[Natural Language Processing Pipeline to Annotate Bulgarian Legislative Documents](https://aclanthology.org/2020.lrec-1.863) (Koeva et al., LREC 2020)
ACL