Unsupervised Methods for Syntactic Structure Induction
Projektseminar: Computerlinguistik, B.Sc./M.Sc.Leitung: Christoph Teichmann
Ort: C7 1 Besprechungsraum U15
Zeit: Mo 12-14
Beginn: ab 31.10.2016
Geeignet für: B.Sc./M.Sc.
Since 2000 there have been a number of advancements in unsupervised learning for natural language processing and unsupervised approaches are becoming more and more useful in exploiting large amounts of data that can be used to supplement smaller annotated training sets. In this seminar we will examine how syntactic annotation, i.e. Part-Of-Speech tags, dependency and constituency trees, can be generated without the use of manual annotation. We will discuss research papers and you will try out a number of implementations. In order to be able to fully understand the content of the papers, we will also review some Machine Learning concepts if necessary.
More information will be posted here: Course Page