@inproceedings{skorzewski-etal-2022-named,
title = "Named Entity Recognition to Detect Criminal Texts on the Web",
author = "Sk{\'o}rzewski, Pawe{\l} and
Pieniowski, Miko{\l}aj and
Demenko, Grazyna",
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-1.669",
pages = "6223--6231",
abstract = "This paper presents a toolkit that applies named-entity extraction techniques to identify information related to criminal activity in texts from the Polish Internet. The methodological and technical assumptions were established following the requirements of our application users from the Border Guard. Due to the specificity of the users{'} needs and the specificity of web texts, we used original methodologies related to the search for desired texts, the creation of domain lexicons, the annotation of the collected text resources, and the combination of rule-based and machine-learning techniques for extracting the information desired by the user. The performance of our tools has been evaluated on 6240 manually annotated text fragments collected from Internet sources. Evaluation results and user feedback show that our approach is feasible and has potential value for real-life applications in the daily work of border guards. Lexical lookup combined with hand-crafted rules and regular expressions, supported by text statistics, can make a decent specialized entity recognition system in the absence of large data sets required for training a good neural network.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skorzewski-etal-2022-named">
<titleInfo>
<title>Named Entity Recognition to Detect Criminal Texts on the Web</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Skórzewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikołaj</namePart>
<namePart type="family">Pieniowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grazyna</namePart>
<namePart type="family">Demenko</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>This paper presents a toolkit that applies named-entity extraction techniques to identify information related to criminal activity in texts from the Polish Internet. The methodological and technical assumptions were established following the requirements of our application users from the Border Guard. Due to the specificity of the users’ needs and the specificity of web texts, we used original methodologies related to the search for desired texts, the creation of domain lexicons, the annotation of the collected text resources, and the combination of rule-based and machine-learning techniques for extracting the information desired by the user. The performance of our tools has been evaluated on 6240 manually annotated text fragments collected from Internet sources. Evaluation results and user feedback show that our approach is feasible and has potential value for real-life applications in the daily work of border guards. Lexical lookup combined with hand-crafted rules and regular expressions, supported by text statistics, can make a decent specialized entity recognition system in the absence of large data sets required for training a good neural network.</abstract>
<identifier type="citekey">skorzewski-etal-2022-named</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.669</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6223</start>
<end>6231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition to Detect Criminal Texts on the Web
%A Skórzewski, Paweł
%A Pieniowski, Mikołaj
%A Demenko, Grazyna
%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 skorzewski-etal-2022-named
%X This paper presents a toolkit that applies named-entity extraction techniques to identify information related to criminal activity in texts from the Polish Internet. The methodological and technical assumptions were established following the requirements of our application users from the Border Guard. Due to the specificity of the users’ needs and the specificity of web texts, we used original methodologies related to the search for desired texts, the creation of domain lexicons, the annotation of the collected text resources, and the combination of rule-based and machine-learning techniques for extracting the information desired by the user. The performance of our tools has been evaluated on 6240 manually annotated text fragments collected from Internet sources. Evaluation results and user feedback show that our approach is feasible and has potential value for real-life applications in the daily work of border guards. Lexical lookup combined with hand-crafted rules and regular expressions, supported by text statistics, can make a decent specialized entity recognition system in the absence of large data sets required for training a good neural network.
%U https://aclanthology.org/2022.lrec-1.669
%P 6223-6231
Markdown (Informal)
[Named Entity Recognition to Detect Criminal Texts on the Web](https://aclanthology.org/2022.lrec-1.669) (Skórzewski et al., LREC 2022)
ACL