@inproceedings{orasmaa-etal-2022-named,
title = "Named Entity Recognition in {E}stonian 19th Century Parish Court Records",
author = "Orasmaa, Siim and
Muischnek, Kadri and
Poska, Kristjan and
Edela, Anna",
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-1.568",
pages = "5304--5313",
abstract = "This paper presents a new historical language resource, a corpus of Estonian Parish Court records from the years 1821-1920, annotated for named entities (NE), and reports on named entity recognition (NER) experiments using this corpus. The hand-written records have been transcribed manually via a crowdsourcing project, so the transcripts are of high quality, but the variation of language and spelling is high in these documents due to dialectal variation and the fact that there was a considerable change in Estonian spelling conventions during the time of their writing. The typology of NEs for manual annotation includes 7 categories, but the inter-annotator agreement is as good as 95.0 (mean F1-score). We experimented with fine-tuning BERT-like transfer learning approaches for NER, and found modern Estonian BERT models highly applicable, despite the difficulty of the historical material. Our best model, finetuned Est-RoBERTa, achieved microaverage F1 score of 93.6, which is comparable to state-of-the-art NER performance on the contemporary Estonian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orasmaa-etal-2022-named">
<titleInfo>
<title>Named Entity Recognition in Estonian 19th Century Parish Court Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siim</namePart>
<namePart type="family">Orasmaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kadri</namePart>
<namePart type="family">Muischnek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristjan</namePart>
<namePart type="family">Poska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Edela</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>This paper presents a new historical language resource, a corpus of Estonian Parish Court records from the years 1821-1920, annotated for named entities (NE), and reports on named entity recognition (NER) experiments using this corpus. The hand-written records have been transcribed manually via a crowdsourcing project, so the transcripts are of high quality, but the variation of language and spelling is high in these documents due to dialectal variation and the fact that there was a considerable change in Estonian spelling conventions during the time of their writing. The typology of NEs for manual annotation includes 7 categories, but the inter-annotator agreement is as good as 95.0 (mean F1-score). We experimented with fine-tuning BERT-like transfer learning approaches for NER, and found modern Estonian BERT models highly applicable, despite the difficulty of the historical material. Our best model, finetuned Est-RoBERTa, achieved microaverage F1 score of 93.6, which is comparable to state-of-the-art NER performance on the contemporary Estonian.</abstract>
<identifier type="citekey">orasmaa-etal-2022-named</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.568</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5304</start>
<end>5313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition in Estonian 19th Century Parish Court Records
%A Orasmaa, Siim
%A Muischnek, Kadri
%A Poska, Kristjan
%A Edela, Anna
%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 orasmaa-etal-2022-named
%X This paper presents a new historical language resource, a corpus of Estonian Parish Court records from the years 1821-1920, annotated for named entities (NE), and reports on named entity recognition (NER) experiments using this corpus. The hand-written records have been transcribed manually via a crowdsourcing project, so the transcripts are of high quality, but the variation of language and spelling is high in these documents due to dialectal variation and the fact that there was a considerable change in Estonian spelling conventions during the time of their writing. The typology of NEs for manual annotation includes 7 categories, but the inter-annotator agreement is as good as 95.0 (mean F1-score). We experimented with fine-tuning BERT-like transfer learning approaches for NER, and found modern Estonian BERT models highly applicable, despite the difficulty of the historical material. Our best model, finetuned Est-RoBERTa, achieved microaverage F1 score of 93.6, which is comparable to state-of-the-art NER performance on the contemporary Estonian.
%U https://aclanthology.org/2022.lrec-1.568
%P 5304-5313
Markdown (Informal)
[Named Entity Recognition in Estonian 19th Century Parish Court Records](https://aclanthology.org/2022.lrec-1.568) (Orasmaa et al., LREC 2022)
ACL