A tutorial entitled “Understanding and Using UBY” will be presented by Dr. Judith Eckle-Kohler and Dr. Christian M. Meyer of the UKP Lab on 15 May 2015 from 10:00 to 13:00. The tutorial will take place in Room S115/133 (Institute of Psychology) of Technische Universität Darmstadt.

The goal of this tutorial is to gain a fundamental understanding of the lexical resource UBY and its usage in natural language processing applications (e.g., for feature extraction in machine learning tasks or as a knowledge base for the lexical-semantic annotation of text).

Outline and estimated schedule

Learning unit 1 (~ 85 min)

• Overview of UBY and the UBY-LMF model

• Working with dictionary information

• Working with wordnet information

• Working with multilingual and sense-linked information

• OntoWiktionary as a prototype of a structurally enriched resource

(Coffee break)

Learning unit 2 (~ 85 min)

• Working with deep semantic information

• Working with syntactic information

• Using UBY as a UIMA resource

• Use case: semantic tagging with UBY

• Use case: extracting features from UBY

Wrap-up

Preparation

This tutorial contains interactive parts. Please bring a laptop with a development environment if you are interested to try UBY hands-on. We will announce more details before the tutorial.

Tutorial instructors

Judith Eckle-Kohler is a Senior Researcher in the Ubiquitous Knowledge Processing (UKP) Lab at the University of Darmstadt. Her research focuses on the automatic acquisition of lexical resources and their use for large-scale semantic text processing. She studied Computer Science at Stuttgart University and did her Ph.D. in Computational Linguistics on the automatic acquisition of a German subcategorization lexicon. For the last four years, she has been leading the development of the large-scale lexical resource UBY and extensively published on this topic.

Christian M. Meyer is a post-doctoral fellow at the Ubiquitous Knowledge Processing (UKP) Lab, Technische Universität Darmstadt. His research interests include intelligent writing assistance and knowledge-based approaches with a particular focus on innovative applications for lexical resources. He has expertise in sense-linking and standardization of lexical resources, word sense disambiguation, and inter-rater agreement. His dissertation at the intersection of electronic lexicography and natural language processing addressed the collaboratively created online lexicon Wiktionary. In his master’s thesis, he developed a question answering system, which has been awarded the GSCL price for the best student thesis 2009–2011.