Neural Dependency Parsing of Morphologically-Rich Languages



Language and Computation Courses

Advanced Course

Neural Dependency Parsing of Morphologically-Rich Languages,
Erhard Hinrichs (University of Tübingen, Germany) and Daniël de Kok (University of Tübingen, Germany)

Week 1, 17:00 – 18:30, Room 243, Floor 2

This course will introduce parsing of morphologically-rich languages using neural transition-based dependency parsers. Until recently, most work on neural transition-based dependency parsing was conducted on English. However, with the recent introduction of the Universal Dependency annotation scheme and corresponding treebanks for 50 languages (De Marneffe et al., 2014; Nivre et al., 2016), it seems timely to explore neural transition-based dependency parsing for other languages. In this course, we will focus on morphologically-rich languages and will draw on our own dependency parsing research as one use case of this kind. More generally, we will discuss how information about the macrostructure of different clause types (de Kok and Hinrichs, 2016) and about word-level morphology (de Kok, 2015; Ballesteros et al., 2015) can substantially improve parsing accuracy for such languages. We will further show how recurrent neural networks can be used to model such information.

Course survey

If you are participating in our course, it would be great if you could fill out the following survey, to give us more insight into your background and what topics interest you the most:

Slides and literature

Course slides and literature will be uploaded after each lecture.

Day 1

Dependency grammar & Transition-based dependency parsers

Day 2

Transition-based dependency parsers & linear classification

Day 3

Feed forward neural networks

Day 4

Morphology & word representations

Day 5

Recurrent Neural Networks for parsing