Saved in:
Bibliographic Details
Main Authors: Athukoralage, Dasun, Atapattu, Thushari, Thilakaratne, Menasha, Falkner, Katrina
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.07759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909222186254336
author Athukoralage, Dasun
Atapattu, Thushari
Thilakaratne, Menasha
Falkner, Katrina
author_facet Athukoralage, Dasun
Atapattu, Thushari
Thilakaratne, Menasha
Falkner, Katrina
contents This paper presents our approaches for the SMM4H24 Shared Task 5 on the binary classification of English tweets reporting children's medical disorders. Our first approach involves fine-tuning a single RoBERTa-large model, while the second approach entails ensembling the results of three fine-tuned BERTweet-large models. We demonstrate that although both approaches exhibit identical performance on validation data, the BERTweet-large ensemble excels on test data. Our best-performing system achieves an F1-score of 0.938 on test data, outperforming the benchmark classifier by 1.18%.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LT4SG@SMM4H24: Tweets Classification for Digital Epidemiology of Childhood Health Outcomes Using Pre-Trained Language Models
Athukoralage, Dasun
Atapattu, Thushari
Thilakaratne, Menasha
Falkner, Katrina
Computation and Language
This paper presents our approaches for the SMM4H24 Shared Task 5 on the binary classification of English tweets reporting children's medical disorders. Our first approach involves fine-tuning a single RoBERTa-large model, while the second approach entails ensembling the results of three fine-tuned BERTweet-large models. We demonstrate that although both approaches exhibit identical performance on validation data, the BERTweet-large ensemble excels on test data. Our best-performing system achieves an F1-score of 0.938 on test data, outperforming the benchmark classifier by 1.18%.
title LT4SG@SMM4H24: Tweets Classification for Digital Epidemiology of Childhood Health Outcomes Using Pre-Trained Language Models
topic Computation and Language
url https://arxiv.org/abs/2406.07759