@inproceedings{pokrywka-etal-2022-challenging,
title = "Challenging {A}merica: Modeling language in longer time scales",
author = "Pokrywka, Jakub and
Grali{\'n}ski, Filip and
Jassem, Krzysztof and
Kaczmarek, Karol and
Jurkiewicz, Krzysztof and
Wierzchon, Piotr",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.56",
doi = "10.18653/v1/2022.findings-naacl.56",
pages = "737--749",
abstract = "The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i.e. pre-train and fine-tune large Transformer models. This paper introduces an ML challenge, named Challenging America (ChallAm), based on OCR-ed excerpts from historical newspapers collected from the Chronicling America portal. ChallAm provides a dataset of clippings, labeled with metadata on their origin, and paired with their textual contents retrieved by an OCR tool. Three, publicly available, ML tasks are defined in the challenge: to determine the article date, to detect the location of the issue, and to deduce a word in a text gap (cloze test). Strong baselines are provided for all three ChallAm tasks. In particular, we pre-trained a RoBERTa model from scratch from the historical texts. We also discuss the issues of discrimination and hate-speech present in the historical American texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pokrywka-etal-2022-challenging">
<titleInfo>
<title>Challenging America: Modeling language in longer time scales</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Pokrywka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Jassem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Kaczmarek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Jurkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Wierzchon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i.e. pre-train and fine-tune large Transformer models. This paper introduces an ML challenge, named Challenging America (ChallAm), based on OCR-ed excerpts from historical newspapers collected from the Chronicling America portal. ChallAm provides a dataset of clippings, labeled with metadata on their origin, and paired with their textual contents retrieved by an OCR tool. Three, publicly available, ML tasks are defined in the challenge: to determine the article date, to detect the location of the issue, and to deduce a word in a text gap (cloze test). Strong baselines are provided for all three ChallAm tasks. In particular, we pre-trained a RoBERTa model from scratch from the historical texts. We also discuss the issues of discrimination and hate-speech present in the historical American texts.</abstract>
<identifier type="citekey">pokrywka-etal-2022-challenging</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.56</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.56</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>737</start>
<end>749</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenging America: Modeling language in longer time scales
%A Pokrywka, Jakub
%A Graliński, Filip
%A Jassem, Krzysztof
%A Kaczmarek, Karol
%A Jurkiewicz, Krzysztof
%A Wierzchon, Piotr
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F pokrywka-etal-2022-challenging
%X The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i.e. pre-train and fine-tune large Transformer models. This paper introduces an ML challenge, named Challenging America (ChallAm), based on OCR-ed excerpts from historical newspapers collected from the Chronicling America portal. ChallAm provides a dataset of clippings, labeled with metadata on their origin, and paired with their textual contents retrieved by an OCR tool. Three, publicly available, ML tasks are defined in the challenge: to determine the article date, to detect the location of the issue, and to deduce a word in a text gap (cloze test). Strong baselines are provided for all three ChallAm tasks. In particular, we pre-trained a RoBERTa model from scratch from the historical texts. We also discuss the issues of discrimination and hate-speech present in the historical American texts.
%R 10.18653/v1/2022.findings-naacl.56
%U https://aclanthology.org/2022.findings-naacl.56
%U https://doi.org/10.18653/v1/2022.findings-naacl.56
%P 737-749
Markdown (Informal)
[Challenging America: Modeling language in longer time scales](https://aclanthology.org/2022.findings-naacl.56) (Pokrywka et al., Findings 2022)
ACL
- Jakub Pokrywka, Filip Graliński, Krzysztof Jassem, Karol Kaczmarek, Krzysztof Jurkiewicz, and Piotr Wierzchon. 2022. Challenging America: Modeling language in longer time scales. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 737–749, Seattle, United States. Association for Computational Linguistics.