@inproceedings{wolinski-etal-2022-herbert,
title = "{H}er{BERT} Based Language Model Detects Quantifiers and Their Semantic Properties in {P}olish",
author = "Woli{\'n}ski, Marcin and
Nito{\'n}, Bart{\l}omiej and
Kiera{\'s}, Witold and
Szymanik, Jakub",
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-1.773",
pages = "7140--7146",
abstract = "The paper presents a tool for automatic marking up of quantifying expressions, their semantic features, and scopes. We explore the idea of using a BERT based neural model for the task (in this case HerBERT, a model trained specifically for Polish, is used). The tool is trained on a recent manually annotated Corpus of Polish Quantificational Expressions (Szymanik and Kiera{\'s}, 2022). We discuss how it performs against human annotation and present results of automatic annotation of 300 million sub-corpus of National Corpus of Polish. Our results show that language models can effectively recognise semantic category of quantification as well as identify key semantic properties of quantifiers, like monotonicity. Furthermore, the algorithm we have developed can be used for building semantically annotated quantifier corpora for other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wolinski-etal-2022-herbert">
<titleInfo>
<title>HerBERT Based Language Model Detects Quantifiers and Their Semantic Properties in Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Woliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartłomiej</namePart>
<namePart type="family">Nitoń</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Witold</namePart>
<namePart type="family">Kieraś</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Szymanik</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>The paper presents a tool for automatic marking up of quantifying expressions, their semantic features, and scopes. We explore the idea of using a BERT based neural model for the task (in this case HerBERT, a model trained specifically for Polish, is used). The tool is trained on a recent manually annotated Corpus of Polish Quantificational Expressions (Szymanik and Kieraś, 2022). We discuss how it performs against human annotation and present results of automatic annotation of 300 million sub-corpus of National Corpus of Polish. Our results show that language models can effectively recognise semantic category of quantification as well as identify key semantic properties of quantifiers, like monotonicity. Furthermore, the algorithm we have developed can be used for building semantically annotated quantifier corpora for other languages.</abstract>
<identifier type="citekey">wolinski-etal-2022-herbert</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.773</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7140</start>
<end>7146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HerBERT Based Language Model Detects Quantifiers and Their Semantic Properties in Polish
%A Woliński, Marcin
%A Nitoń, Bartłomiej
%A Kieraś, Witold
%A Szymanik, Jakub
%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 wolinski-etal-2022-herbert
%X The paper presents a tool for automatic marking up of quantifying expressions, their semantic features, and scopes. We explore the idea of using a BERT based neural model for the task (in this case HerBERT, a model trained specifically for Polish, is used). The tool is trained on a recent manually annotated Corpus of Polish Quantificational Expressions (Szymanik and Kieraś, 2022). We discuss how it performs against human annotation and present results of automatic annotation of 300 million sub-corpus of National Corpus of Polish. Our results show that language models can effectively recognise semantic category of quantification as well as identify key semantic properties of quantifiers, like monotonicity. Furthermore, the algorithm we have developed can be used for building semantically annotated quantifier corpora for other languages.
%U https://aclanthology.org/2022.lrec-1.773
%P 7140-7146
Markdown (Informal)
[HerBERT Based Language Model Detects Quantifiers and Their Semantic Properties in Polish](https://aclanthology.org/2022.lrec-1.773) (Woliński et al., LREC 2022)
ACL