Skip to content

Add rules or suffix search? #4

@johann-petrak

Description

@johann-petrak

Since German has arbitrary composita, a purely lookup-based lemmatiser will often fail because of OOV words. But in many cases a guess that is better than nothing at all could be to combine the prefix with the lemma of a known suffix, e.g: lemma("Mithelferinnen" ) = "Mit"+lemma("Helferinnen").

Are there any plans to add support for composita?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions