https://github.com/cothema/nlp-tools

https://github.com/cothema/nlp-tools

Last synced: about 10 hours ago
JSON representation

• Host: GitHub
• URL: https://github.com/cothema/nlp-tools
• Owner: cothema
• License: mit
• Created: 2021-03-24T22:19:02.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-03-29T19:15:41.000Z (over 3 years ago)
• Last Synced: 2024-10-08T15:38:26.304Z (about 1 month ago)
• Language: TypeScript
• Size: 802 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Security: SECURITY.md

Awesome Lists containing this project

README

        
# Cothema NLP Static Tools

Simple javascript natual language processing static tools.

## CZ edu webpages

- https://eprehledy.cz/

## General useful tools

- https://cloud.google.com/natural-language/automl/docs/languages

- https://www.kaggle.com/ For data science (datasets)

- https://www.tensorflow.org/js

## Other links

- https://monkeylearn.com

## Similar tools for inspiration / for use

- https://github.com/spencermountain/compromise

- https://github.com/NaturalNode/natural

## Basic NLP guides

- https://monkeylearn.com/blog/definitive-guide-natural-language-processing/

- https://towardsdatascience.com/a-practitioners-guide-to-natural-language-processing-part-i-processing-understanding-text-9f4abfd13e72

## Supported languages

- Czech

## Terminology

|Term|Meaning|

|---|---|

|Tokenization|Tokenization is the process of **chopping** character streams into tokens" (Manning, Raghavan and Schutze, 2008).|