@inproceedings{hadifar-etal-2021-million,
title = "A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks",
author = "Hadifar, Amir and
Labat, Sofie and
Hoste, Veronique and
Develder, Chris and
Demeester, Thomas",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.21/",
doi = "10.18653/v1/2021.naacl-main.21",
pages = "220--225",
abstract = "In online domain-specific customer service applications, many companies struggle to deploy advanced NLP models successfully, due to the limited availability of and noise in their datasets. While prior research demonstrated the potential of migrating large open-domain pretrained models for domain-specific tasks, the appropriate (pre)training strategies have not yet been rigorously evaluated in such social media customer service settings, especially under multilingual conditions. We address this gap by collecting a multilingual social media corpus containing customer service conversations (865k tweets), comparing various pipelines of pretraining and finetuning approaches, applying them on 5 different end tasks. We show that pretraining a generic multilingual transformer model on our in-domain dataset, before finetuning on specific end tasks, consistently boosts performance, especially in non-English settings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hadifar-etal-2021-million">
<titleInfo>
<title>A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hadifar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofie</namePart>
<namePart type="family">Labat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Develder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Demeester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In online domain-specific customer service applications, many companies struggle to deploy advanced NLP models successfully, due to the limited availability of and noise in their datasets. While prior research demonstrated the potential of migrating large open-domain pretrained models for domain-specific tasks, the appropriate (pre)training strategies have not yet been rigorously evaluated in such social media customer service settings, especially under multilingual conditions. We address this gap by collecting a multilingual social media corpus containing customer service conversations (865k tweets), comparing various pipelines of pretraining and finetuning approaches, applying them on 5 different end tasks. We show that pretraining a generic multilingual transformer model on our in-domain dataset, before finetuning on specific end tasks, consistently boosts performance, especially in non-English settings.</abstract>
<identifier type="citekey">hadifar-etal-2021-million</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.21</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.21/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>220</start>
<end>225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks
%A Hadifar, Amir
%A Labat, Sofie
%A Hoste, Veronique
%A Develder, Chris
%A Demeester, Thomas
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F hadifar-etal-2021-million
%X In online domain-specific customer service applications, many companies struggle to deploy advanced NLP models successfully, due to the limited availability of and noise in their datasets. While prior research demonstrated the potential of migrating large open-domain pretrained models for domain-specific tasks, the appropriate (pre)training strategies have not yet been rigorously evaluated in such social media customer service settings, especially under multilingual conditions. We address this gap by collecting a multilingual social media corpus containing customer service conversations (865k tweets), comparing various pipelines of pretraining and finetuning approaches, applying them on 5 different end tasks. We show that pretraining a generic multilingual transformer model on our in-domain dataset, before finetuning on specific end tasks, consistently boosts performance, especially in non-English settings.
%R 10.18653/v1/2021.naacl-main.21
%U https://aclanthology.org/2021.naacl-main.21/
%U https://doi.org/10.18653/v1/2021.naacl-main.21
%P 220-225
Markdown (Informal)
[A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks](https://aclanthology.org/2021.naacl-main.21/) (Hadifar et al., NAACL 2021)
ACL