تقرير
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning
| العنوان: | CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning |
|---|---|
| المؤلفون: | Liu, Xiaoming, Zhang, Zhaohan, Wang, Yichen, Pu, Hang, Lan, Yu, Shen, Chao |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language |
| الوصف: | Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed detectors usually take coarse text sequences as input and fine-tune pretrained models with standard cross-entropy loss. However, these methods fail to consider the linguistic structure of texts. Moreover, they lack the ability to handle the low-resource problem which could often happen in practice considering the enormous amount of textual data online. In this paper, we present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. To exploit the linguistic feature, we encode coherence information in form of graph into text representation. To tackle the challenges of low data resource, we employ a contrastive learning framework and propose an improved contrastive loss for preventing performance degradation brought by simple samples. The experiment results on two public datasets and two self-constructed datasets prove our approach outperforms the state-of-art methods significantly. Also, we surprisingly find that MGTs originated from up-to-date language models could be easier to detect than these from previous models, in our experiments. And we propose some preliminary explanations for this counter-intuitive phenomena. All the codes and datasets are open-sourced. Comment: Accepted by EMNLP 2023 main cofference |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2212.10341 |
| رقم الأكسشن: | edsarx.2212.10341 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |