People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F23%3A00130934" target="_blank" >RIV/00216224:14330/23:00130934 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.findings-acl.887" target="_blank" >https://aclanthology.org/2023.findings-acl.887</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts

Popis výsledku v původním jazyce

<p>Although pre-trained named entity recognition (NER) models are highly accurate on modern corpora, they underperform on historical texts due to differences in language OCR errors. In this work, we develop a new NER corpus of 3.6M sentences from late medieval charters written mainly in Czech, Latin, and German.</p> <p>We show that we can start with a list of known historical figures and locations and an unannotated corpus of historical texts, and use information retrieval techniques to automatically bootstrap a NER-annotated corpus. Using our corpus, we train a NER model that achieves entity-level Precision of 72.81-93.98% with 58.14-81.77% Recall on a manually-annotated test dataset. Furthermore, we show that using a weighted loss function helps to combat class imbalance in token classification tasks. To make it easy for others to reproduce and build upon our work, we publicly release our corpus, models, and experimental code.</p>

Název v anglickém jazyce

People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts

Popis výsledku anglicky

<p>Although pre-trained named entity recognition (NER) models are highly accurate on modern corpora, they underperform on historical texts due to differences in language OCR errors. In this work, we develop a new NER corpus of 3.6M sentences from late medieval charters written mainly in Czech, Latin, and German.</p> <p>We show that we can start with a list of known historical figures and locations and an unannotated corpus of historical texts, and use information retrieval techniques to automatically bootstrap a NER-annotated corpus. Using our corpus, we train a NER model that achieves entity-level Precision of 72.81-93.98% with 58.14-81.77% Recall on a manually-annotated test dataset. Furthermore, we show that using a weighted loss function helps to combat class imbalance in token classification tasks. To make it easy for others to reproduce and build upon our work, we publicly release our corpus, models, and experimental code.</p>

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Findings of the Association for Computational Linguistics: ACL 2023

ISBN

9781959429623

ISSN

0736-587X

e-ISSN

—

Počet stran výsledku

10

Strana od-do

14104-14113

Název nakladatele

Association for Computational Linguistics

Místo vydání

Toronto, Canada

Místo konání akce

Toronto, Canada

Datum konání akce

9. 7. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—