@inproceedings{nakwijit-etal-2023-lexicools,
title = "Lexicools at {S}em{E}val-2023 Task 10: Sexism Lexicon Construction via {XAI}",
author = "Nakwijit, Pakawat and
Samir, Mahmoud and
Purver, Matthew",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.4",
doi = "10.18653/v1/2023.semeval-1.4",
pages = "23--43",
abstract = "This paper presents our work on the SemEval-2023 Task 10 Explainable Detection of Online Sexism (EDOS) using lexicon-based models. Our approach consists of three main steps: lexicon construction based on Pointwise Mutual Information (PMI) and Shapley value, lexicon augmentation using an unannotated corpus and Large Language Models (LLMs), and, lastly, lexical incorporation for Bag-of-Word (BoW) logistic regression and fine-tuning LLMs. Our results demonstrate that our Shapley approach effectively produces a high-quality lexicon. We also show that by simply counting the presence of certain words in our lexicons and comparing the count can outperform a BoW logistic regression in task B/C and fine-tuning BERT in task C. In the end, our classifier achieved F1-scores of 53.34{\textbackslash}{\%} and 27.31{\textbackslash}{\%} on the official blind test sets for tasks B and C, respectively. We, additionally, provide in-depth analysis highlighting model limitation and bias. We also present our attempts to understand the model{'}s behaviour based on our constructed lexicons. Our code and the resulting lexicons are open-sourced in our GitHub repository \url{https://github.com/SirBadr/SemEval2022-Task10}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakwijit-etal-2023-lexicools">
<titleInfo>
<title>Lexicools at SemEval-2023 Task 10: Sexism Lexicon Construction via XAI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pakawat</namePart>
<namePart type="family">Nakwijit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Samir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our work on the SemEval-2023 Task 10 Explainable Detection of Online Sexism (EDOS) using lexicon-based models. Our approach consists of three main steps: lexicon construction based on Pointwise Mutual Information (PMI) and Shapley value, lexicon augmentation using an unannotated corpus and Large Language Models (LLMs), and, lastly, lexical incorporation for Bag-of-Word (BoW) logistic regression and fine-tuning LLMs. Our results demonstrate that our Shapley approach effectively produces a high-quality lexicon. We also show that by simply counting the presence of certain words in our lexicons and comparing the count can outperform a BoW logistic regression in task B/C and fine-tuning BERT in task C. In the end, our classifier achieved F1-scores of 53.34\textbackslash% and 27.31\textbackslash% on the official blind test sets for tasks B and C, respectively. We, additionally, provide in-depth analysis highlighting model limitation and bias. We also present our attempts to understand the model’s behaviour based on our constructed lexicons. Our code and the resulting lexicons are open-sourced in our GitHub repository https://github.com/SirBadr/SemEval2022-Task10.</abstract>
<identifier type="citekey">nakwijit-etal-2023-lexicools</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.4</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.4</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>23</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicools at SemEval-2023 Task 10: Sexism Lexicon Construction via XAI
%A Nakwijit, Pakawat
%A Samir, Mahmoud
%A Purver, Matthew
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F nakwijit-etal-2023-lexicools
%X This paper presents our work on the SemEval-2023 Task 10 Explainable Detection of Online Sexism (EDOS) using lexicon-based models. Our approach consists of three main steps: lexicon construction based on Pointwise Mutual Information (PMI) and Shapley value, lexicon augmentation using an unannotated corpus and Large Language Models (LLMs), and, lastly, lexical incorporation for Bag-of-Word (BoW) logistic regression and fine-tuning LLMs. Our results demonstrate that our Shapley approach effectively produces a high-quality lexicon. We also show that by simply counting the presence of certain words in our lexicons and comparing the count can outperform a BoW logistic regression in task B/C and fine-tuning BERT in task C. In the end, our classifier achieved F1-scores of 53.34\textbackslash% and 27.31\textbackslash% on the official blind test sets for tasks B and C, respectively. We, additionally, provide in-depth analysis highlighting model limitation and bias. We also present our attempts to understand the model’s behaviour based on our constructed lexicons. Our code and the resulting lexicons are open-sourced in our GitHub repository https://github.com/SirBadr/SemEval2022-Task10.
%R 10.18653/v1/2023.semeval-1.4
%U https://aclanthology.org/2023.semeval-1.4
%U https://doi.org/10.18653/v1/2023.semeval-1.4
%P 23-43
Markdown (Informal)
[Lexicools at SemEval-2023 Task 10: Sexism Lexicon Construction via XAI](https://aclanthology.org/2023.semeval-1.4) (Nakwijit et al., SemEval 2023)
ACL