Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data
Li, Yufei, Yu, Xiao, Liu, Yanchi, Chen, Haifeng, Liu, Cong
–arXiv.org Artificial Intelligence
Jointly extracting entity pairs and their relations is challenging when working on distantly-supervised data with ambiguous or noisy labels. To mitigate such impact, we propose uncertainty-aware bootstrap learning, which is motivated by the intuition that the higher uncertainty of an instance, the more likely the model confidence is inconsistent with the ground truths. Specifically, we first explore instance-level data uncertainty to create an initial high-confident examples. Such subset serves as filtering noisy instances and facilitating the model to converge fast at the early stage. During bootstrap learning, we propose self-ensembling as a regularizer to alleviate inter-model uncertainty produced by noisy labels. We further define probability variance of joint tagging probabilities to estimate inner-model parametric uncertainty, which is used to select and build up new reliable training instances for the next iteration. Experimental results on two large datasets reveal that our approach outperforms existing strong baselines and related methods.
arXiv.org Artificial Intelligence
Jun-8-2023
- Country:
- South America > Chile
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- New York
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- New York County > New York City (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.28)
- Maryland > Montgomery County
- Gaithersburg (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Riverside County > Riverside (0.04)
- Los Angeles County > Long Beach (0.04)
- New York
- Canada > Ontario
- Toronto (0.04)
- Europe
- France (0.04)
- Germany > Berlin (0.04)
- Spain
- Italy > Tuscany
- Florence (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Asia
- Singapore (0.04)
- China > Hong Kong (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- Japan > Honshū
- Kansai > Osaka Prefecture > Osaka (0.04)
- Genre:
- Research Report (0.40)
- Technology: