MasonTigers@LT-EDI-2024: An Ensemble Approach Towards Detecting Homophobia and Transphobia in Social Media Comments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goswami, Dhiman, Puspo, Sadiya Sayara Chowdhury, Raihan, Md Nishat, Emran, Al Nahian Bin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913234892619776
author Goswami, Dhiman
Puspo, Sadiya Sayara Chowdhury
Raihan, Md Nishat
Emran, Al Nahian Bin
author_facet Goswami, Dhiman
Puspo, Sadiya Sayara Chowdhury
Raihan, Md Nishat
Emran, Al Nahian Bin
contents In this paper, we describe our approaches and results for Task 2 of the LT-EDI 2024 Workshop, aimed at detecting homophobia and/or transphobia across ten languages. Our methodologies include monolingual transformers and ensemble methods, capitalizing on the strengths of each to enhance the performance of the models. The ensemble models worked well, placing our team, MasonTigers, in the top five for eight of the ten languages, as measured by the macro F1 score. Our work emphasizes the efficacy of ensemble methods in multilingual scenarios, addressing the complexities of language-specific tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14681
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MasonTigers@LT-EDI-2024: An Ensemble Approach Towards Detecting Homophobia and Transphobia in Social Media Comments
Goswami, Dhiman
Puspo, Sadiya Sayara Chowdhury
Raihan, Md Nishat
Emran, Al Nahian Bin
Computation and Language
In this paper, we describe our approaches and results for Task 2 of the LT-EDI 2024 Workshop, aimed at detecting homophobia and/or transphobia across ten languages. Our methodologies include monolingual transformers and ensemble methods, capitalizing on the strengths of each to enhance the performance of the models. The ensemble models worked well, placing our team, MasonTigers, in the top five for eight of the ten languages, as measured by the macro F1 score. Our work emphasizes the efficacy of ensemble methods in multilingual scenarios, addressing the complexities of language-specific tasks.
title MasonTigers@LT-EDI-2024: An Ensemble Approach Towards Detecting Homophobia and Transphobia in Social Media Comments
topic Computation and Language
url https://arxiv.org/abs/2401.14681