@inproceedings{liu-etal-2022-leveraging,
title = "Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification",
author = "Liu, Yang and
Chordia, Varnith and
Li, Hua and
Fazeli Dehkordy, Siavash and
Sun, Yifei and
Gao, Vincent and
Zhang, Na",
editor = "Malmasi, Shervin and
Rokhlenko, Oleg and
Ueffing, Nicola and
Guy, Ido and
Agichtein, Eugene and
Kallumadi, Surya",
booktitle = "Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ecnlp-1.3",
doi = "10.18653/v1/2022.ecnlp-1.3",
pages = "20--28",
abstract = "In a leading e-commerce business, we receive hundreds of millions of customer feedback from different text communication channels such as product reviews. The feedback can contain rich information regarding customers{'} dissatisfaction in the quality of goods and services. To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text. We identify issues at two levels: coarse grained (L-Coarse) and fine grained (L-Granular). We formulate this multi-level product issue identification problem as a seq2seq language generation problem. Specifically, we utilize transformer-based seq2seq models due to their versatility and strong transfer-learning capability. We demonstrate that our approach is label efficient and outperforms the traditional approach such as multi-class multi-label classification formulation. Based on human evaluation, our fine-tuned model achieves 82.1{\%} and 95.4{\%} human-level performance for L-Coarse and L-Granular issue identification, respectively. Furthermore, our experiments illustrate that the model can generalize to identify unseen L-Granular issues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-leveraging">
<titleInfo>
<title>Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varnith</namePart>
<namePart type="family">Chordia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siavash</namePart>
<namePart type="family">Fazeli Dehkordy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Na</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Rokhlenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Ueffing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Guy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Agichtein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surya</namePart>
<namePart type="family">Kallumadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In a leading e-commerce business, we receive hundreds of millions of customer feedback from different text communication channels such as product reviews. The feedback can contain rich information regarding customers’ dissatisfaction in the quality of goods and services. To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text. We identify issues at two levels: coarse grained (L-Coarse) and fine grained (L-Granular). We formulate this multi-level product issue identification problem as a seq2seq language generation problem. Specifically, we utilize transformer-based seq2seq models due to their versatility and strong transfer-learning capability. We demonstrate that our approach is label efficient and outperforms the traditional approach such as multi-class multi-label classification formulation. Based on human evaluation, our fine-tuned model achieves 82.1% and 95.4% human-level performance for L-Coarse and L-Granular issue identification, respectively. Furthermore, our experiments illustrate that the model can generalize to identify unseen L-Granular issues.</abstract>
<identifier type="citekey">liu-etal-2022-leveraging</identifier>
<identifier type="doi">10.18653/v1/2022.ecnlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.ecnlp-1.3</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>20</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification
%A Liu, Yang
%A Chordia, Varnith
%A Li, Hua
%A Fazeli Dehkordy, Siavash
%A Sun, Yifei
%A Gao, Vincent
%A Zhang, Na
%Y Malmasi, Shervin
%Y Rokhlenko, Oleg
%Y Ueffing, Nicola
%Y Guy, Ido
%Y Agichtein, Eugene
%Y Kallumadi, Surya
%S Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F liu-etal-2022-leveraging
%X In a leading e-commerce business, we receive hundreds of millions of customer feedback from different text communication channels such as product reviews. The feedback can contain rich information regarding customers’ dissatisfaction in the quality of goods and services. To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text. We identify issues at two levels: coarse grained (L-Coarse) and fine grained (L-Granular). We formulate this multi-level product issue identification problem as a seq2seq language generation problem. Specifically, we utilize transformer-based seq2seq models due to their versatility and strong transfer-learning capability. We demonstrate that our approach is label efficient and outperforms the traditional approach such as multi-class multi-label classification formulation. Based on human evaluation, our fine-tuned model achieves 82.1% and 95.4% human-level performance for L-Coarse and L-Granular issue identification, respectively. Furthermore, our experiments illustrate that the model can generalize to identify unseen L-Granular issues.
%R 10.18653/v1/2022.ecnlp-1.3
%U https://aclanthology.org/2022.ecnlp-1.3
%U https://doi.org/10.18653/v1/2022.ecnlp-1.3
%P 20-28
Markdown (Informal)
[Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification](https://aclanthology.org/2022.ecnlp-1.3) (Liu et al., ECNLP 2022)
ACL