Skip to content

Commit

Permalink
roadmap update
Browse files Browse the repository at this point in the history
  • Loading branch information
perayson committed Aug 19, 2024
1 parent 2afc3e9 commit 50c03c0
Showing 1 changed file with 5 additions and 5 deletions.
10 changes: 5 additions & 5 deletions ROADMAP.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,15 +10,15 @@ This document outlines our high level plans for expected developments in PyMUSAS
- Inclusion of the Finnish semantic lexicons and spaCy tagging pipeline into pymusas (released 11th May 2022)
- Open release of the English semantic lexicons in the [Multilingual USAS repository](https://github.com/UCREL/Multilingual-USAS) (released 1st June 2022)
- Incorporation of English semantic tagger into the pymusas spaCy pipeline (released 2nd June 2022)
- Set up simple web page interface on http://ucrel-api.lancaster.ac.uk/ and REST API (17th February 2023)
- Inclusion into Wmatrix6 (12th May 2023)

## Ongoing development (by end June 2022)
## Ongoing development
- Further development of English, Spanish, Dutch and Danish system and lexicons (as part of the [4D Picture project](https://4dpicture.eu/))

- Set up simple web page interface on http://ucrel-api.lancaster.ac.uk/ and REST API

## Future development (in 2022 or later; funding dependent)
## Future development (funding dependent)

- Further development of Spanish, German, French, Dutch and Danish system and lexicons
- Further extensions to other languages or to incorporate POS taggers and lemmatisers beyond the list of languages supported by spaCy: Finnish (with a new compound engine), Arabic (with CAMeL tools), Korean, Persian, Spanish (with Grampal POS tagger), Urdu (with UNLT POS tagger)
- Further disambiguation methods e.g. vector based, machine learning, deep learning
- Creation and release of gold and/or silver standard corpora
- Inclusion into Wmatrix

0 comments on commit 50c03c0

Please sign in to comment.