@inproceedings{hammami-etal-2024-fighting,
title = "Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data",
author = "Hammami, Haitham and
Baligand, Louis and
Petrovski, Bojan",
editor = "Yang, Yi and
Davani, Aida and
Sil, Avi and
Kumar, Anoop",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-industry.17",
doi = "10.18653/v1/2024.naacl-industry.17",
pages = "201--212",
abstract = "In the financial industry, identifying the location of parties involved in payments is a major challenge in the context of Anti-Money Laundering transaction monitoring. For this purpose address parsing entails extracting fields such as street, postal code, or country from free text message attributes. While payment processing platforms are updating their standards with more structured formats such as SWIFT with ISO 20022, address parsing remains essential for a considerable volume of messages. With the emergence of Transformers and Generative Large Language Models (LLM), we explore the performance of state-of-the-art solutions given the constraint of processing a vast amount of daily data. This paper also aims to show the need for training robust models capable of dealing with real-world noisy transactional data. Our results suggest that a well fine-tuned Transformer model using early-stopping significantly outperforms other approaches. Nevertheless, generative LLMs demonstrate strong zero{\_}shot performance and warrant further investigations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hammami-etal-2024-fighting">
<titleInfo>
<title>Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haitham</namePart>
<namePart type="family">Hammami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">Baligand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojan</namePart>
<namePart type="family">Petrovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the financial industry, identifying the location of parties involved in payments is a major challenge in the context of Anti-Money Laundering transaction monitoring. For this purpose address parsing entails extracting fields such as street, postal code, or country from free text message attributes. While payment processing platforms are updating their standards with more structured formats such as SWIFT with ISO 20022, address parsing remains essential for a considerable volume of messages. With the emergence of Transformers and Generative Large Language Models (LLM), we explore the performance of state-of-the-art solutions given the constraint of processing a vast amount of daily data. This paper also aims to show the need for training robust models capable of dealing with real-world noisy transactional data. Our results suggest that a well fine-tuned Transformer model using early-stopping significantly outperforms other approaches. Nevertheless, generative LLMs demonstrate strong zero_shot performance and warrant further investigations.</abstract>
<identifier type="citekey">hammami-etal-2024-fighting</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-industry.17</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-industry.17</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>201</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data
%A Hammami, Haitham
%A Baligand, Louis
%A Petrovski, Bojan
%Y Yang, Yi
%Y Davani, Aida
%Y Sil, Avi
%Y Kumar, Anoop
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F hammami-etal-2024-fighting
%X In the financial industry, identifying the location of parties involved in payments is a major challenge in the context of Anti-Money Laundering transaction monitoring. For this purpose address parsing entails extracting fields such as street, postal code, or country from free text message attributes. While payment processing platforms are updating their standards with more structured formats such as SWIFT with ISO 20022, address parsing remains essential for a considerable volume of messages. With the emergence of Transformers and Generative Large Language Models (LLM), we explore the performance of state-of-the-art solutions given the constraint of processing a vast amount of daily data. This paper also aims to show the need for training robust models capable of dealing with real-world noisy transactional data. Our results suggest that a well fine-tuned Transformer model using early-stopping significantly outperforms other approaches. Nevertheless, generative LLMs demonstrate strong zero_shot performance and warrant further investigations.
%R 10.18653/v1/2024.naacl-industry.17
%U https://aclanthology.org/2024.naacl-industry.17
%U https://doi.org/10.18653/v1/2024.naacl-industry.17
%P 201-212
Markdown (Informal)
[Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data](https://aclanthology.org/2024.naacl-industry.17) (Hammami et al., NAACL 2024)
ACL