Bernd Bohnet, November 08, 2016

Generalized Transition-based Dependency Parsing and the Paradigm Change to Neural Networks 


Parsing technique are besides the machine learning approach the most essential and intensively researched part of natural language analysis systems. 
In this talk, I will sketch the fundamental parsing techniques in dependency parsing and present based on this a generalized parsing framework 
where parsers are instantiated in terms of a set of control parameters that constrain transitions between parser states. 
This generalization provides a unified framework to describe and compare various transition-based parsing approaches from both a theoretical and empirical perspective. 
This includes well-known transition systems, but also previously unstudied systems. 
Finally, I will address the impact of the change of the machine learning paradigm to deep learning which has quite some impact on the used parsing technique.