Questioning the Scope of SRL

Learn about questioning the motivation behind learning SRL.

We are alone when faced with a real-life project. We have a job to do, and the only people to satisfy are those who asked for that project.

Pragmatism must come first. Technical ideology after.

In the 2020s, former AI ideology and new ideology coexist. By the end of the decade, there will be only one winner merging some of the former into the latter.

This lesson questions the productivity of SRL and also its motivation through two aspects:

  • The limit of predicate analysis.

  • Questioning the use of the term “semantic.”

The limit of predicate analysis

SRL relies on predicates. SRL BERT only works as long as we provide a verb. But millions of sentences do not contain verbs.

If we provide SRL BERT in the “Semantic Role Labeling” section in the AllenNLP demo interface with an assertion alone, it works.

But what happens if our assertion is an answer to a question? For example:

  • Person 1: What would you like to drink, please?

  • Person 2: A cup of coffee, please.

When we enter Person 2’s answer, SRL BERT finds nothing:

Get hands-on with 1200+ tech skills courses.