Summary of Team Qust at Semeval-2024 Task 8: a Comprehensive Study Of Monolingual and Multilingual Approaches For Detecting Ai-generated Text, by Xiaoman Xu et al.
Team QUST at SemEval-2024 Task 8: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting AI-generated Text
by Xiaoman Xu, Xiangrun Li, Taihang Wang, Jianxiang Tian, Ye Jiang
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents team QUST’s participation in Task 8 SemEval 2024, focusing on improving model training efficiency and accuracy. The researchers employed various deep-learning methods, including multiscale positive-unlabeled framework (MPU), fine-tuning, adapters, and ensemble methods to tackle the monolingual task. They selected top-performing models based on their accuracy and evaluated them in subtasks A and B. The final model construction combined fine-tuning with MPU using a stacking ensemble approach. QUST’s system achieved 8th place in the official test set for multilingual settings of subtask A, releasing its system code at https://github.com/warmth27/SemEval2024_QUST. This achievement showcases the team’s expertise in developing effective models for natural language processing tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a team called QUST that took part in a competition called SemEval 2024. They worked hard to make their computer program better by using different techniques and combining them to get the best results. The goal was to help computers understand human languages, which is important for things like chatbots and language translation. The team did really well and got an 8th place out of many teams that participated. |
Keywords
» Artificial intelligence » Deep learning » Fine tuning » Natural language processing » Translation
