@inproceedings{zhang-abdul-mageed-2022-improving,
title = "Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning",
author = "Zhang, Chiyu and
Abdul-Mageed, Muhammad",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Barriere, Valentin and
Tafreshi, Shabnam and
Alqahtani, Sawsan and
Sedoc, Jo{\~a}o and
Klinger, Roman and
Balahur, Alexandra",
booktitle = "Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment {\&} Social Media Analysis",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wassa-1.14",
doi = "10.18653/v1/2022.wassa-1.14",
pages = "141--156",
abstract = "Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on 15 different Twitter datasets for social meaning detection. Our methods achieve 2.34{\%} $F_1$ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets. Our methods also excel in few-shot learning: with only 5{\%} of training data (severely few-shot), our methods enable an impressive 68.54{\%} average $F_1$. The methods are also language agnostic, as we show in a zero-shot setting involving six datasets from three different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-abdul-mageed-2022-improving">
<titleInfo>
<title>Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chiyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</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 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis</title>
</titleInfo>
<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">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">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</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">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</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>Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on 15 different Twitter datasets for social meaning detection. Our methods achieve 2.34% F₁ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets. Our methods also excel in few-shot learning: with only 5% of training data (severely few-shot), our methods enable an impressive 68.54% average F₁. The methods are also language agnostic, as we show in a zero-shot setting involving six datasets from three different languages.</abstract>
<identifier type="citekey">zhang-abdul-mageed-2022-improving</identifier>
<identifier type="doi">10.18653/v1/2022.wassa-1.14</identifier>
<location>
<url>https://aclanthology.org/2022.wassa-1.14</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>141</start>
<end>156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning
%A Zhang, Chiyu
%A Abdul-Mageed, Muhammad
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Alqahtani, Sawsan
%Y Sedoc, João
%Y Klinger, Roman
%Y Balahur, Alexandra
%S Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F zhang-abdul-mageed-2022-improving
%X Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on 15 different Twitter datasets for social meaning detection. Our methods achieve 2.34% F₁ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets. Our methods also excel in few-shot learning: with only 5% of training data (severely few-shot), our methods enable an impressive 68.54% average F₁. The methods are also language agnostic, as we show in a zero-shot setting involving six datasets from three different languages.
%R 10.18653/v1/2022.wassa-1.14
%U https://aclanthology.org/2022.wassa-1.14
%U https://doi.org/10.18653/v1/2022.wassa-1.14
%P 141-156
Markdown (Informal)
[Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning](https://aclanthology.org/2022.wassa-1.14) (Zhang & Abdul-Mageed, WASSA 2022)
ACL