This is the course page for the seminar course Dependency Treebanks and Dependency Parsing at the Department of Linguistics, University of Tübingen.
This is a seminar course on dependency analysis of natural language sentences. In essence, we will have a two-part course, where the first part is concerned with how to analyze natural language sentences using dependencies, and create treebanks containing dependency annotations. The second part is about training data-driven parsers on such treebanks. The form of the classes will be a mixture of lectures, and discussion sessions.
This course aims to attract students from two different backgrounds, and facilitate exchange between them. Both students with linguistics and computational background are welcome to participate.
Grading will be based on class participation and homeworks (6ECTS). Further course credits can be obtained by a term project described in a term paper (9ECTS) within the scope of the course. Possible project topics include, building a small, proof-of-concept treebank (preferably for a low resource language); treebank error detection and error correction; using multi-lingual treebanks investigating linguistic variation; or focused experiments on parsing (e.g., for low-resource or morphologically complex languages, transfer learning for parsing, incremental parsing, the use parsing for practical tasks).
Requirements
There are no formal requirements. However, to be able to participate in the second part, you should be able to read and understand research papers on computational linguistics.
Contact
- Instructor: Çağrı Çöltekin
<ccoltekin@sfs.uni-tuebingen.de>
Office hours: Monday 10:00 - 11:00 (Wilhelmstr. 19, room 1.09)