Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages
Wang, Shunjie, Steinert-Threlkeld, Shane
–arXiv.org Artificial Intelligence
Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their implications in modeling natural language, which is hypothesized to be mildly context-sensitive. We test the Transformer's ability to learn mildly context-sensitive languages of varying complexities, and find that they generalize well to unseen in-distribution data, but their ability to extrapolate to longer strings is worse than that of LSTMs. Our analyses show that the learned self-attention patterns and representations modeled dependency relations and demonstrated counting behavior, which may have helped the models solve the languages.
arXiv.org Artificial Intelligence
Oct-19-2023
- Country:
- Oceania > Australia
- North America > United States
- California > Santa Clara County > Stanford (0.04)
- Europe
- Germany > Berlin (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Netherlands > South Holland
- Dordrecht (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Asia
- China > Hong Kong (0.04)
- South Korea (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- Japan > Honshū
- Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- Genre:
- Research Report
- New Finding (0.48)
- Experimental Study (0.48)
- Research Report
- Technology: