@inproceedings{cheniki-etal-2024-multi,
title = "Multi-Property Multi-Label Documents Metadata Recommendation based on Encoder Embeddings",
author = {Cheniki, Nasredine and
Daudaravicius, Vidas and
Feliachi, Abdelfettah and
Hardy, Didier and
K{\"u}ster, Marc Wilhelm},
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Spanakis, Gerasimos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nllp-1.19",
pages = "233--242",
abstract = "The task of document classification, particularly multi-label classification, presents a significant challenge due to the complexity of assigning multiple relevant labels to each document. This complexity is further amplified in multi-property multi-label classification tasks, where documents must be categorized across various sets of labels. In this research, we introduce an innovative encoder embedding-driven approach to multi-property multi-label document classification that leverages semantic-text similarity and the reuse of pre-existing annotated data to enhance the efficiency and accuracy of the document annotation process. Our method requires only a single model for text similarity, eliminating the need for multiple property-specific classifiers and thereby reducing computational demands and simplifying deployment. We evaluate our approach through a prototype deployed for daily operations, which demonstrates superior performance over existing classification systems. Our contributions include improved accuracy without additional training, increased efficiency, and demonstrated effectiveness in practical applications. The results of our study indicate the potential of our approach to be applied across various domains requiring multi-property multi-label document classification, offering a scalable and adaptable solution for metadata annotation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheniki-etal-2024-multi">
<titleInfo>
<title>Multi-Property Multi-Label Documents Metadata Recommendation based on Encoder Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasredine</namePart>
<namePart type="family">Cheniki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidas</namePart>
<namePart type="family">Daudaravicius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelfettah</namePart>
<namePart type="family">Feliachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Didier</namePart>
<namePart type="family">Hardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="given">Wilhelm</namePart>
<namePart type="family">Küster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of document classification, particularly multi-label classification, presents a significant challenge due to the complexity of assigning multiple relevant labels to each document. This complexity is further amplified in multi-property multi-label classification tasks, where documents must be categorized across various sets of labels. In this research, we introduce an innovative encoder embedding-driven approach to multi-property multi-label document classification that leverages semantic-text similarity and the reuse of pre-existing annotated data to enhance the efficiency and accuracy of the document annotation process. Our method requires only a single model for text similarity, eliminating the need for multiple property-specific classifiers and thereby reducing computational demands and simplifying deployment. We evaluate our approach through a prototype deployed for daily operations, which demonstrates superior performance over existing classification systems. Our contributions include improved accuracy without additional training, increased efficiency, and demonstrated effectiveness in practical applications. The results of our study indicate the potential of our approach to be applied across various domains requiring multi-property multi-label document classification, offering a scalable and adaptable solution for metadata annotation tasks.</abstract>
<identifier type="citekey">cheniki-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.19</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>233</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Property Multi-Label Documents Metadata Recommendation based on Encoder Embeddings
%A Cheniki, Nasredine
%A Daudaravicius, Vidas
%A Feliachi, Abdelfettah
%A Hardy, Didier
%A Küster, Marc Wilhelm
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F cheniki-etal-2024-multi
%X The task of document classification, particularly multi-label classification, presents a significant challenge due to the complexity of assigning multiple relevant labels to each document. This complexity is further amplified in multi-property multi-label classification tasks, where documents must be categorized across various sets of labels. In this research, we introduce an innovative encoder embedding-driven approach to multi-property multi-label document classification that leverages semantic-text similarity and the reuse of pre-existing annotated data to enhance the efficiency and accuracy of the document annotation process. Our method requires only a single model for text similarity, eliminating the need for multiple property-specific classifiers and thereby reducing computational demands and simplifying deployment. We evaluate our approach through a prototype deployed for daily operations, which demonstrates superior performance over existing classification systems. Our contributions include improved accuracy without additional training, increased efficiency, and demonstrated effectiveness in practical applications. The results of our study indicate the potential of our approach to be applied across various domains requiring multi-property multi-label document classification, offering a scalable and adaptable solution for metadata annotation tasks.
%U https://aclanthology.org/2024.nllp-1.19
%P 233-242
Markdown (Informal)
[Multi-Property Multi-Label Documents Metadata Recommendation based on Encoder Embeddings](https://aclanthology.org/2024.nllp-1.19) (Cheniki et al., NLLP 2024)
ACL