MasonTigers at SemEval-2024 Task 8: Performance Analysis of Transformer-based Models on Machine-Generated Text Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916194505719808 |
|---|---|
| author | Puspo, Sadiya Sayara Chowdhury Raihan, Md Nishat Goswami, Dhiman Emran, Al Nahian Bin Ganguly, Amrita Uzuner, Ozlem |
| author_facet | Puspo, Sadiya Sayara Chowdhury Raihan, Md Nishat Goswami, Dhiman Emran, Al Nahian Bin Ganguly, Amrita Uzuner, Ozlem |
| contents | This paper presents the MasonTigers entry to the SemEval-2024 Task 8 - Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. The task encompasses Binary Human-Written vs. Machine-Generated Text Classification (Track A), Multi-Way Machine-Generated Text Classification (Track B), and Human-Machine Mixed Text Detection (Track C). Our best performing approaches utilize mainly the ensemble of discriminator transformer models along with sentence transformer and statistical machine learning approaches in specific cases. Moreover, zero-shot prompting and fine-tuning of FLAN-T5 are used for Track A and B. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14989 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MasonTigers at SemEval-2024 Task 8: Performance Analysis of Transformer-based Models on Machine-Generated Text Detection Puspo, Sadiya Sayara Chowdhury Raihan, Md Nishat Goswami, Dhiman Emran, Al Nahian Bin Ganguly, Amrita Uzuner, Ozlem Computation and Language This paper presents the MasonTigers entry to the SemEval-2024 Task 8 - Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. The task encompasses Binary Human-Written vs. Machine-Generated Text Classification (Track A), Multi-Way Machine-Generated Text Classification (Track B), and Human-Machine Mixed Text Detection (Track C). Our best performing approaches utilize mainly the ensemble of discriminator transformer models along with sentence transformer and statistical machine learning approaches in specific cases. Moreover, zero-shot prompting and fine-tuning of FLAN-T5 are used for Track A and B. |
| title | MasonTigers at SemEval-2024 Task 8: Performance Analysis of Transformer-based Models on Machine-Generated Text Detection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.14989 |