Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies
This work addresses parsing semantic graphs for NLP researchers, representing an incremental improvement with specific gains.
The paper tackled semantic dependency parsing by proposing an iterative predicate selection algorithm that combines graph-based and transition-based approaches, achieving a new state of-the-art on SemEval 2015 Task 18 datasets.
In Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the graph-based and transition-based parsing approaches in order to handle multiple semantic head words. We train the IPS model using a combination of multi-task learning and task-specific policy gradient training. Trained this way, IPS achieves a new state of the art on the SemEval 2015 Task 18 datasets. Furthermore, we observe that policy gradient training learns an easy-first strategy.