@inproceedings{huang-etal-2021-user,
title = "User Factor Adaptation for User Embedding via Multitask Learning",
author = "Huang, Xiaolei and
Paul, Michael J. and
Dernoncourt, Franck and
Burke, Robin and
Dredze, Mark",
editor = "Ben-David, Eyal and
Cohen, Shay and
McDonald, Ryan and
Plank, Barbara and
Reichart, Roi and
Rotman, Guy and
Ziser, Yftah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.18/",
pages = "172--182",
abstract = "Language varies across users and their interested fields in social media data: words authored by a user across his/her interests may have different meanings (e.g., cool) or sentiments (e.g., fast). However, most of the existing methods to train user embeddings ignore the variations across user interests, such as product and movie categories (e.g., drama vs. action). In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets. We then propose a user embedding model to account for the language variability of user interests via a multitask learning framework. The model learns user language and its variations without human supervision. While existing work mainly evaluated the user embedding by extrinsic tasks, we propose an intrinsic evaluation via clustering and evaluate user embeddings by an extrinsic task, text classification. The experiments on the three English-language social media datasets show that our proposed approach can generally outperform baselines via adapting the user factor."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2021-user">
<titleInfo>
<title>User Factor Adaptation for User Embedding via Multitask Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaolei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Burke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dredze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Ben-David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Rotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language varies across users and their interested fields in social media data: words authored by a user across his/her interests may have different meanings (e.g., cool) or sentiments (e.g., fast). However, most of the existing methods to train user embeddings ignore the variations across user interests, such as product and movie categories (e.g., drama vs. action). In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets. We then propose a user embedding model to account for the language variability of user interests via a multitask learning framework. The model learns user language and its variations without human supervision. While existing work mainly evaluated the user embedding by extrinsic tasks, we propose an intrinsic evaluation via clustering and evaluate user embeddings by an extrinsic task, text classification. The experiments on the three English-language social media datasets show that our proposed approach can generally outperform baselines via adapting the user factor.</abstract>
<identifier type="citekey">huang-etal-2021-user</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.18/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>172</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T User Factor Adaptation for User Embedding via Multitask Learning
%A Huang, Xiaolei
%A Paul, Michael J.
%A Dernoncourt, Franck
%A Burke, Robin
%A Dredze, Mark
%Y Ben-David, Eyal
%Y Cohen, Shay
%Y McDonald, Ryan
%Y Plank, Barbara
%Y Reichart, Roi
%Y Rotman, Guy
%Y Ziser, Yftah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F huang-etal-2021-user
%X Language varies across users and their interested fields in social media data: words authored by a user across his/her interests may have different meanings (e.g., cool) or sentiments (e.g., fast). However, most of the existing methods to train user embeddings ignore the variations across user interests, such as product and movie categories (e.g., drama vs. action). In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets. We then propose a user embedding model to account for the language variability of user interests via a multitask learning framework. The model learns user language and its variations without human supervision. While existing work mainly evaluated the user embedding by extrinsic tasks, we propose an intrinsic evaluation via clustering and evaluate user embeddings by an extrinsic task, text classification. The experiments on the three English-language social media datasets show that our proposed approach can generally outperform baselines via adapting the user factor.
%U https://aclanthology.org/2021.adaptnlp-1.18/
%P 172-182
Markdown (Informal)
[User Factor Adaptation for User Embedding via Multitask Learning](https://aclanthology.org/2021.adaptnlp-1.18/) (Huang et al., AdaptNLP 2021)
ACL