Paper: Projecting the Knowledge Graph to Syntactic Parsing

ACL ID E14-4006
Title Projecting the Knowledge Graph to Syntactic Parsing
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014

We present a syntactic parser training paradigm that learns from large scale Knowledge Bases. By utilizing the Knowledge Base context only during training, the resulting parser has no inference-time dependency on the Knowl- edge Base, thus not decreasing the speed during prediction. Knowledge Base infor- mation is injected into the model using an extension to the Augmented-loss training framework. We present empirical results that show this approach achieves a signif- icant gain in accuracy for syntactic cat- egories such as coordination and apposi- tion.