-
Would love to do to POS tagging with this lib
Maybe integrate with others?
https://github.com/FinNLP/en-pos
-
- [x] process text function to get tokens
- [x] Stemming Example
- [x] Parts of Speech(POS) Tagging example
- [x] Create frequency distribution and compute unigram probability
- [x] Create conditi…
-
Perform parts of speech tagging on prompt to only return nouns.
-
https://universaldependencies.org/ has labelled data for parts of speech, dependencies and information about morphology for Hindi, Sanskrit, Marathi, Tamil and Telugu.
I plan on using a LM-LSTM-CRF a…
-
Would be cool to browse by categories. Some examples:
- Parts of speech
- Proper noun types: names, places, etc.
- Word origins: phonetic loanwords, semantic loanwords, onomatopoeia
- Usages: f…
-
Hanlp may currently be the best Chinese segmentation engine, with much better segmentation results than Jieba.
I am trying to use Hanlp to segment all the Markdown documents locally and then creat…
-
When I do tokenization Japanese, displayed "ValueError: Package 'pos2.ja' not found in index".
But, I installed TASK:post and TASK:unipos and pos2.ja package is not found
>>> t = "あ、ちなみにどっちの意味で適齢…
-
Look into using NLP to extract data from text.
-
Today's meeting was rather informative. We went over how to use the git command line in relevance to our project. After overcoming some initial technical issues concerning Git, we drew up a quick pre-…
-
Here would agree a series of tests using the same test text(s), and compare performance in a set of agreed tasks. This would provide a nice way of seeing how the various packages and approaches work f…