Whether you're a researcher, data scientist, or engineer, TNLTK is the ideal choice for your Turkish language NLP needs. With its comprehensive suite of tools and its focus on accuracy, TNLTK is the premier library for working with Turkish text data.
Full Changelog: https://github.com/tnltk/tnltk/commits/v0.1.2
pip install tnltk
TNLTK is a Natural Language Processing (NLP) library for Turkish language. The first version includes SentenceSplitter, Deasciifier, and Normalizer modules. The SentenceSplitter module allows for the separation of a text into sentences by considering Turkish non-breaking prefixes. The Deasciifier module converts an ASCII-only string to a Turkish string, taking into account the context of the surrounding characters during the conversion process. The Normalizer module contains methods to convert numbers in a given text to words in Turkish, remove punctuations and accent marks, and convert a string of text to lowercase for Turkish language.
This means that the library is still in the early stages of development and may contain bugs and unfinished features. We are continuously working to stabilize experimental features and add documentation, but users should be aware that the library is not yet fully tested or ready for production use. We appreciate your interest in TNLTK and encourage you to try it out and provide feedback to help us improve the library.