Structured prediction

Dependency parsing

Level

Basic (22 points)

In this lab, you will implement a simplified version of the dependency parser presented by Glavaš and Vulić (2021), consisting of a transformer encoder followed by a bi-affine layer that computes arc scores for all pairs of words. You will evaluate the parser on a treebank from the Universal Dependencies Project.

• Paper by Glavaš and Vulić (2021)
• Link to the basic lab

Projectivisation

Level

Advanced (33 points)

In this lab you will implement the Eisner algorithm for projective dependency parsing and use it to transform (possibly non-projective) dependency trees to projective trees. This transformation is necessary to be able to apply algorithms for projective dependency parsing to treebanks that may contain non-projective trees.

• Video lecture about the Eisner algorithm
• Link to the advanced lab