Saved in:
Bibliographic Details
Main Authors: Marchitan, Teodor-George, Creanga, Claudiu, Dinu, Liviu P.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.17964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913366804529152
author Marchitan, Teodor-George
Creanga, Claudiu
Dinu, Liviu P.
author_facet Marchitan, Teodor-George
Creanga, Claudiu
Dinu, Liviu P.
contents This paper describes the approach of the UniBuc - NLP team in tackling the SemEval 2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. We explored transformer-based and hybrid deep learning architectures. For subtask B, our transformer-based model achieved a strong \textbf{second-place} out of $77$ teams with an accuracy of \textbf{86.95\%}, demonstrating the architecture's suitability for this task. However, our models showed overfitting in subtask A which could potentially be fixed with less fine-tunning and increasing maximum sequence length. For subtask C (token-level classification), our hybrid model overfit during training, hindering its ability to detect transitions between human and machine-generated text.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transformer and Hybrid Deep Learning Based Models for Machine-Generated Text Detection
Marchitan, Teodor-George
Creanga, Claudiu
Dinu, Liviu P.
Computation and Language
This paper describes the approach of the UniBuc - NLP team in tackling the SemEval 2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. We explored transformer-based and hybrid deep learning architectures. For subtask B, our transformer-based model achieved a strong \textbf{second-place} out of $77$ teams with an accuracy of \textbf{86.95\%}, demonstrating the architecture's suitability for this task. However, our models showed overfitting in subtask A which could potentially be fixed with less fine-tunning and increasing maximum sequence length. For subtask C (token-level classification), our hybrid model overfit during training, hindering its ability to detect transitions between human and machine-generated text.
title Transformer and Hybrid Deep Learning Based Models for Machine-Generated Text Detection
topic Computation and Language
url https://arxiv.org/abs/2405.17964