https://github.com/cltk/old-norse-lemmatizer
https://github.com/cltk/old-norse-lemmatizer
inflection lemmatizer nlp old-norse
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/cltk/old-norse-lemmatizer
- Owner: cltk
- Created: 2019-02-18T10:07:33.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-10T23:11:49.000Z (over 6 years ago)
- Last Synced: 2025-02-17T08:41:42.532Z (8 months ago)
- Topics: inflection, lemmatizer, nlp, old-norse
- Language: Jupyter Notebook
- Size: 49.8 KB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Old Norse lemmatizer
The main aim of this repository is to generate all the forms that Old Norse words can have, given the Zoëga's
dictionary and the Old Norse inflection rules.
## TODOs
* [x] Retrieve lemmata of the [Zoëga's dictionary](https://github.com/cltk/old_norse_dictionary_zoega).
* [ ] For each lemma, extract the word category (noun, verb, pronoun, article, number, etc). One lemma can represent several word categories.
* [ ] For a given lemma in a certain word category, extract the precise subcategory: a verbs may be strong, weak or preterite-present, nouns can be strong or weak, masculine, feminine or neuter, etc.
* [ ] For a given lemma with its precise word category, generate all the possible forms that a lemma can have thanks to [Old Norse lemma inflection module of CLTK](https://github.com/cltk/cltk/tree/master/cltk/inflection/old_norse).
* [ ] Compute frequencies of each word forms in Old Norse corpora.
* [ ] Make lemmatizers for Old Norse.