Discussion: Using dependency parsing

[bdura]

Description

We might benefit from using a parse tree.

Parsing is a most transverse task, and could provide an easy way to create baselines for many pipeline components (qualifiers, linking events, etc).

However, this is uncharted territory for me. A few questions:

• Has anyone tried using models trained on non-speciality French language in the clinical setting?
• If re-training is needed, do you have an idea of the effort that's needed in terms of annotation?

Any thoughts?

[percevalw]

This could be interesting. However, I see two blocking points, which are precisely those you raise:

• the performances on the French clinic are not always up to scratch. Enumerations, sections, and other specificities of the clinic are often not correctly detected
• annotation is long and tedious (https://link.springer.com/chapter/10.1007/978-94-010-0201-1_10).

Maybe we could just re-annotate the specific formulas of the clinical domain but I have no doubt that this would require a significant effort.