On the Sequence Evaluation based on Stochastic Processes
Zhang, Tianhao, Lin, Zhexiao, Sheng, Zhecheng, Jiang, Chen, Kang, Dongyeop
–arXiv.org Artificial Intelligence
Modeling and analyzing long sequences of text is an essential task for Natural Language Processing. Success in capturing long text dynamics using neural language models will facilitate many downstream tasks such as coherence evaluation, text generation, machine translation and so on. This paper presents a novel approach to model sequences through a stochastic process. We introduce a likelihood-based training objective for the text encoder and design a more thorough measurement (score) for long text evaluation compared to the previous approach. The proposed training objective effectively preserves the sequence coherence, while the new score comprehensively captures both temporal and spatial dependencies. Theoretical properties of our new score show its advantages in sequence evaluation. Experimental results show superior performance in various sequence evaluation tasks, including global and local discrimination within and between documents of different lengths. We also demonstrate the encoder achieves competitive results on discriminating human and AI written text.
arXiv.org Artificial Intelligence
Jun-15-2024
- Country:
- South America > Colombia
- Meta Department > Villavicencio (0.04)
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- Minnesota (0.05)
- New York > New York County
- New York City (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- California > Alameda County
- Berkeley (0.04)
- Europe
- Asia
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- China
- Hong Kong (0.04)
- Heilongjiang Province > Daqing (0.04)
- Middle East > UAE
- South America > Colombia
- Genre:
- Research Report > New Finding (0.48)