@inproceedings{soni-etal-2024-comparing,
title = "Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?",
author = "Soni, Nikita and
Balasubramanian, Niranjan and
Schwartz, H. and
Hovy, Dirk",
editor = "De Clercq, Orph{\'e}e and
Barriere, Valentin and
Barnes, Jeremy and
Klinger, Roman and
Sedoc, Jo{\~a}o and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wassa-1.26",
pages = "316--328",
abstract = "Pre-trained language models consider the context of neighboring words and documents but lack any author context of the human generating the text. However, language depends on the author{'}s states, traits, social, situational, and environmental attributes, collectively referred to as human context (Soni et al., 2024). Human-centered natural language processing requires incorporating human context into language models. Currently, two methods exist: pre-training with 1) group-wise attributes (e.g., over-45-year-olds) or 2) individual traits. Group attributes are simple but coarse {---} not all 45-year-olds write the same way {---} while individual traits allow for more personalized representations, but require more complex modeling and data. It is unclear which approach benefits what tasks. We compare pre-training models with human context via 1) group attributes, 2) individual users, and 3) a combined approach on five user- and document-level tasks. Our results show that there is no best approach, but that human-centered language modeling holds avenues for different methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soni-etal-2024-comparing">
<titleInfo>
<title>Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models consider the context of neighboring words and documents but lack any author context of the human generating the text. However, language depends on the author’s states, traits, social, situational, and environmental attributes, collectively referred to as human context (Soni et al., 2024). Human-centered natural language processing requires incorporating human context into language models. Currently, two methods exist: pre-training with 1) group-wise attributes (e.g., over-45-year-olds) or 2) individual traits. Group attributes are simple but coarse — not all 45-year-olds write the same way — while individual traits allow for more personalized representations, but require more complex modeling and data. It is unclear which approach benefits what tasks. We compare pre-training models with human context via 1) group attributes, 2) individual users, and 3) a combined approach on five user- and document-level tasks. Our results show that there is no best approach, but that human-centered language modeling holds avenues for different methods.</abstract>
<identifier type="citekey">soni-etal-2024-comparing</identifier>
<location>
<url>https://aclanthology.org/2024.wassa-1.26</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>316</start>
<end>328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?
%A Soni, Nikita
%A Balasubramanian, Niranjan
%A Schwartz, H.
%A Hovy, Dirk
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Barnes, Jeremy
%Y Klinger, Roman
%Y Sedoc, João
%Y Tafreshi, Shabnam
%S Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F soni-etal-2024-comparing
%X Pre-trained language models consider the context of neighboring words and documents but lack any author context of the human generating the text. However, language depends on the author’s states, traits, social, situational, and environmental attributes, collectively referred to as human context (Soni et al., 2024). Human-centered natural language processing requires incorporating human context into language models. Currently, two methods exist: pre-training with 1) group-wise attributes (e.g., over-45-year-olds) or 2) individual traits. Group attributes are simple but coarse — not all 45-year-olds write the same way — while individual traits allow for more personalized representations, but require more complex modeling and data. It is unclear which approach benefits what tasks. We compare pre-training models with human context via 1) group attributes, 2) individual users, and 3) a combined approach on five user- and document-level tasks. Our results show that there is no best approach, but that human-centered language modeling holds avenues for different methods.
%U https://aclanthology.org/2024.wassa-1.26
%P 316-328
Markdown (Informal)
[Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?](https://aclanthology.org/2024.wassa-1.26) (Soni et al., WASSA-WS 2024)
ACL
- Nikita Soni, Niranjan Balasubramanian, H. Schwartz, and Dirk Hovy. 2024. Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 316–328, Bangkok, Thailand. Association for Computational Linguistics.