Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond
Liu, Siyang, Deng, Naihao, Sabour, Sahand, Jia, Yilin, Huang, Minlie, Mihalcea, Rada
–arXiv.org Artificial Intelligence
We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive tokenizer samples variable segmentations from multiple outcomes, with sampling probabilities optimized based on task-specific data. We introduce a strategy for building a specialized vocabulary and introduce a vocabulary merging protocol that allows for the integration of task-specific tokens into the pre-trained model's tokenization step. Through extensive experiments on psychological question-answering tasks in both Chinese and English, we find that our task-adaptive tokenization approach brings a significant improvement in generation performance while using up to 60% fewer tokens. Preliminary experiments point to promising results when using our tokenization approach with very large language models.
arXiv.org Artificial Intelligence
Nov-13-2023
- Country:
- North America
- United States
- Pennsylvania (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Canada > Ontario
- Toronto (0.04)
- United States
- Europe
- Ireland (0.04)
- Germany > Berlin (0.04)
- Czechia > Prague (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- Nepal (0.04)
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- China > Beijing
- Beijing (0.04)
- North America
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Technology: