D 2023

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

NOVOTNÝ, Vít, Kristýna LUGER, Michal ŠTEFÁNIK, Tereza VRABCOVÁ, Aleš HORÁK et. al.

Basic information

Original name

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

Authors

NOVOTNÝ, Vít (203 Czech Republic, guarantor, belonging to the institution), Kristýna LUGER (203 Czech Republic, belonging to the institution), Michal ŠTEFÁNIK (703 Slovakia, belonging to the institution), Tereza VRABCOVÁ (203 Czech Republic, belonging to the institution) and Aleš HORÁK (203 Czech Republic, belonging to the institution)

Edition

Toronto, Canada, Findings of the Association for Computational Linguistics: ACL 2023, p. 14104-14113, 10 pp. 2023

Publisher

Association for Computational Linguistics

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

RIV identification code

RIV/00216224:14330/23:00130934

Organization unit

Faculty of Informatics

ISBN

978-1-959429-62-3

ISSN

Keywords (in Czech)

zpracování přirozeného jazyka; nlp; historické dokumenty; rozpoznávání textu; ocr; detekce pojmenovaných entit; ner; čeština; němčina; latina

Keywords in English

natural language processing; nlp; historical documents; optical character recognition; ocr; named entity recognition; ner; czech; german; latin

Tags

International impact, Reviewed
Změněno: 7/4/2024 23:02, RNDr. Pavel Šmerk, Ph.D.

Abstract

V originále

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.

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.


Links

MUNI/A/1339/2022, interní kód MU
Name: Rozvoj technik pro zpracování dat pro podporu vyhledávání, analýz a vizualizací rozsáhlých datových souborů s využitím umělé inteligence
Investor: Masaryk University, Development of data processing techniques to support search, analysis and visualization of large datasets using artificial intelligence