@inproceedings{marinova-etal-2020-reconstructing,
title = "Reconstructing {NER} Corpora: a Case Study on {B}ulgarian",
author = "Marinova, Iva and
Laskova, Laska and
Osenova, Petya and
Simov, Kiril and
Popov, Alexander",
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-1.571",
pages = "4647--4652",
abstract = "The paper reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus. We show how the annotations in a type-based corpus of named entities (NE) were populated as occurrences within it, thus ensuring density of the training information. A deep learning model was adopted for discovering inconsistencies in the initial annotation and for learning new NE types. The evaluation results get improved after data curation, randomization and deduplication.",
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="marinova-etal-2020-reconstructing">
<titleInfo>
<title>Reconstructing NER Corpora: a Case Study on Bulgarian</title>
</titleInfo>
<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">Laska</namePart>
<namePart type="family">Laskova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Alexander</namePart>
<namePart type="family">Popov</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 reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus. We show how the annotations in a type-based corpus of named entities (NE) were populated as occurrences within it, thus ensuring density of the training information. A deep learning model was adopted for discovering inconsistencies in the initial annotation and for learning new NE types. The evaluation results get improved after data curation, randomization and deduplication.</abstract>
<identifier type="citekey">marinova-etal-2020-reconstructing</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.571</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>4647</start>
<end>4652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reconstructing NER Corpora: a Case Study on Bulgarian
%A Marinova, Iva
%A Laskova, Laska
%A Osenova, Petya
%A Simov, Kiril
%A Popov, Alexander
%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 marinova-etal-2020-reconstructing
%X The paper reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus. We show how the annotations in a type-based corpus of named entities (NE) were populated as occurrences within it, thus ensuring density of the training information. A deep learning model was adopted for discovering inconsistencies in the initial annotation and for learning new NE types. The evaluation results get improved after data curation, randomization and deduplication.
%U https://aclanthology.org/2020.lrec-1.571
%P 4647-4652
Markdown (Informal)
[Reconstructing NER Corpora: a Case Study on Bulgarian](https://aclanthology.org/2020.lrec-1.571) (Marinova et al., LREC 2020)
ACL
- Iva Marinova, Laska Laskova, Petya Osenova, Kiril Simov, and Alexander Popov. 2020. Reconstructing NER Corpora: a Case Study on Bulgarian. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 4647–4652, Marseille, France. European Language Resources Association.