@inproceedings{marcuzzo-etal-2022-multi,
title = "A multi-level approach for hierarchical Ticket Classification",
author = "Marcuzzo, Matteo and
Zangari, Alessandro and
Schiavinato, Michele and
Giudice, Lorenzo and
Gasparetto, Andrea and
Albarelli, Andrea",
booktitle = "Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wnut-1.22",
pages = "201--214",
abstract = "The automatic categorization of support tickets is a fundamental tool for modern businesses. Such requests are most commonly composed of concise textual descriptions that are noisy and filled with technical jargon. In this paper, we test the effectiveness of pre-trained LMs for the classification of issues related to software bugs. First, we test several strategies to produce single, ticket-wise representations starting from their BERT-generated word embeddings. Then, we showcase a simple yet effective way to build a multi-level classifier for the categorization of documents with two hierarchically dependent labels. We experiment on a public bugs dataset and compare our results with standard BERT-based and traditional SVM classifiers. Our findings suggest that both embedding strategies and hierarchical label dependencies considerably impact classification accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marcuzzo-etal-2022-multi">
<titleInfo>
<title>A multi-level approach for hierarchical Ticket Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Marcuzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Zangari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Schiavinato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Giudice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Gasparetto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Albarelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The automatic categorization of support tickets is a fundamental tool for modern businesses. Such requests are most commonly composed of concise textual descriptions that are noisy and filled with technical jargon. In this paper, we test the effectiveness of pre-trained LMs for the classification of issues related to software bugs. First, we test several strategies to produce single, ticket-wise representations starting from their BERT-generated word embeddings. Then, we showcase a simple yet effective way to build a multi-level classifier for the categorization of documents with two hierarchically dependent labels. We experiment on a public bugs dataset and compare our results with standard BERT-based and traditional SVM classifiers. Our findings suggest that both embedding strategies and hierarchical label dependencies considerably impact classification accuracy.</abstract>
<identifier type="citekey">marcuzzo-etal-2022-multi</identifier>
<location>
<url>https://aclanthology.org/2022.wnut-1.22</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>201</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A multi-level approach for hierarchical Ticket Classification
%A Marcuzzo, Matteo
%A Zangari, Alessandro
%A Schiavinato, Michele
%A Giudice, Lorenzo
%A Gasparetto, Andrea
%A Albarelli, Andrea
%S Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F marcuzzo-etal-2022-multi
%X The automatic categorization of support tickets is a fundamental tool for modern businesses. Such requests are most commonly composed of concise textual descriptions that are noisy and filled with technical jargon. In this paper, we test the effectiveness of pre-trained LMs for the classification of issues related to software bugs. First, we test several strategies to produce single, ticket-wise representations starting from their BERT-generated word embeddings. Then, we showcase a simple yet effective way to build a multi-level classifier for the categorization of documents with two hierarchically dependent labels. We experiment on a public bugs dataset and compare our results with standard BERT-based and traditional SVM classifiers. Our findings suggest that both embedding strategies and hierarchical label dependencies considerably impact classification accuracy.
%U https://aclanthology.org/2022.wnut-1.22
%P 201-214
Markdown (Informal)
[A multi-level approach for hierarchical Ticket Classification](https://aclanthology.org/2022.wnut-1.22) (Marcuzzo et al., WNUT 2022)
ACL
- Matteo Marcuzzo, Alessandro Zangari, Michele Schiavinato, Lorenzo Giudice, Andrea Gasparetto, and Andrea Albarelli. 2022. A multi-level approach for hierarchical Ticket Classification. In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022), pages 201–214, Gyeongju, Republic of Korea. Association for Computational Linguistics.