tonyjurg / tonyjurg/morphkit

Add taging scheme for morphological underspecification

Open
#4 0 comments 0 reactions 1 assignee View on GitHub

@tonyjurg is already working on this.

Since Jan 23, 2026.

enhancement
Dominant language
Jupyter Notebook
Stars
0
Forks
0
PR merge metrics
No merged PRs in 30d

Description

implement an optional tagging scheme able to encode morphological ambiguity stemming from underspecification.

As per page 16 of my thesis Visualising Overlooked Morphosyntactic Alternatives

"Recent work by James Tauber on the MorphGNT dataset illustrates a shift toward more granular and transparent annotation of certain types of morphological ambiguity. He proposes introducing tags that explicitly mark morphological underspecification (for example, labelling a form as “non-feminine” when it could be either masculine or neuter). [47] An example of such a tagging schema appears in his parsing of the SBLGNT, where the article τῶν is tagged both as GPN (indicating functional interpretation) and GPX (indicating grammatical form), with POS information recorded separately. [48] This distinction enables researchers to differentiate underspecification from other forms of ambiguity in a principled way."

[47] James Tauber, “New Draft Morphological Tags for MorphGNT,” accessed 15 July, 2025, https://jktauber.com/2018/02/03/new-draft-morphological-tags-morphgnt/.
[48] See for example this line showing the annotation of τῶν in Jude: James Tauber, “sblgnt/86-Jud-morphgnt.txt,” accessed 15 July, 2025, https://github.com/morphgnt/sblgnt/blob/3b5cbdf92cb5e9bdb48a48026bcc0a08f885dd2c/86-Jud-morphgnt.txt#L290.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.