Publications / Domestic Conferences & Theses
A Dependency Parsing Model with Reinforced Head-Dependent Constraint Rules: Combining Deep Learning and Linguistic Knowledge
Abstract
Through data and error case analysis, expanded the neural symbolic model from two applied rules to 24, developing a state-of-the-art model.
Key Contribution
Expanded neural-symbolic constraint rules from 2 to 24, achieving state-of-the-art dependency parsing.