@inproceedings{borenstein-etal-2023-multilingual,
title = "Multilingual Event Extraction from Historical Newspaper Adverts",
author = "Borenstein, Nadav and
da Silva Perez, Nat{\'a}lia and
Augenstein, Isabelle",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.574",
doi = "10.18653/v1/2023.acl-long.574",
pages = "10304--10325",
abstract = "NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP models are trained on modern language texts, rendering them significantly less effective when applied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper addresses these challenges while focusing on the under-explored task of event extraction from a novel domain of historical texts. We introduce a new multilingual dataset in English, French, and Dutch composed of newspaper ads from the early modern colonial period reporting on enslaved people who liberated themselves from enslavement. We find that: 1) even with scarce annotated data, it is possible to achieve surprisingly good results by formulating the problem as an extractive QA task and leveraging existing datasets and models for modern languages; and 2) cross-lingual low-resource learning for historical languages is highly challenging, and machine translation of the historical datasets to the considered target languages is, in practice, often the best-performing solution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borenstein-etal-2023-multilingual">
<titleInfo>
<title>Multilingual Event Extraction from Historical Newspaper Adverts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadav</namePart>
<namePart type="family">Borenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natália</namePart>
<namePart type="family">da Silva Perez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP models are trained on modern language texts, rendering them significantly less effective when applied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper addresses these challenges while focusing on the under-explored task of event extraction from a novel domain of historical texts. We introduce a new multilingual dataset in English, French, and Dutch composed of newspaper ads from the early modern colonial period reporting on enslaved people who liberated themselves from enslavement. We find that: 1) even with scarce annotated data, it is possible to achieve surprisingly good results by formulating the problem as an extractive QA task and leveraging existing datasets and models for modern languages; and 2) cross-lingual low-resource learning for historical languages is highly challenging, and machine translation of the historical datasets to the considered target languages is, in practice, often the best-performing solution.</abstract>
<identifier type="citekey">borenstein-etal-2023-multilingual</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.574</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.574</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10304</start>
<end>10325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Event Extraction from Historical Newspaper Adverts
%A Borenstein, Nadav
%A da Silva Perez, Natália
%A Augenstein, Isabelle
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F borenstein-etal-2023-multilingual
%X NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP models are trained on modern language texts, rendering them significantly less effective when applied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper addresses these challenges while focusing on the under-explored task of event extraction from a novel domain of historical texts. We introduce a new multilingual dataset in English, French, and Dutch composed of newspaper ads from the early modern colonial period reporting on enslaved people who liberated themselves from enslavement. We find that: 1) even with scarce annotated data, it is possible to achieve surprisingly good results by formulating the problem as an extractive QA task and leveraging existing datasets and models for modern languages; and 2) cross-lingual low-resource learning for historical languages is highly challenging, and machine translation of the historical datasets to the considered target languages is, in practice, often the best-performing solution.
%R 10.18653/v1/2023.acl-long.574
%U https://aclanthology.org/2023.acl-long.574
%U https://doi.org/10.18653/v1/2023.acl-long.574
%P 10304-10325
Markdown (Informal)
[Multilingual Event Extraction from Historical Newspaper Adverts](https://aclanthology.org/2023.acl-long.574) (Borenstein et al., ACL 2023)
ACL
- Nadav Borenstein, Natália da Silva Perez, and Isabelle Augenstein. 2023. Multilingual Event Extraction from Historical Newspaper Adverts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10304–10325, Toronto, Canada. Association for Computational Linguistics.