trankit
NLP toolkit
A lightweight toolkit for multilingual natural language processing tasks using transformer-based architectures.
Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
736 stars
21 watching
102 forks
Language: Python
last commit: about 1 month ago
Linked from 1 awesome list
adaptersartificial-intelligencedeeplearningdependency-parsinglanguage-modellemmatizationmachine-learningmorphological-taggingmultilingualnatural-language-processingnlppart-of-speech-taggingpytorchsentence-segmentationtokenizationuniversal-dependenciesxlm-roberta
Related projects:
Repository | Description | Stars |
---|---|---|
goru001/inltk | A comprehensive toolkit for Natural Language Processing tasks in Indic languages, providing pre-trained models and datasets. | 822 |
cltk/cltk | A Python library offering natural language processing capabilities for pre-modern languages | 839 |
nlpodyssey/cybertron | A Go package providing an easy interface to use pre-trained NLP models from the HuggingFace repository for tasks like text classification and machine translation. | 286 |
backprop-ai/backprop | A Python library that provides pre-trained models and tools for fine-tuning and deploying natural language processing tasks | 243 |
wichert/lingua | A tool to simplify translating software source code and check existing translations. | 46 |
helsinki-nlp/ukrainianlt | A collection of Ukrainian language tools and resources for machine translation, natural language processing, and text translation. | 30 |
citiususc/linguakit | A multilingual NLP toolkit providing various natural language processing tasks | 65 |
adobe/nlp-cube | A framework providing a set of Natural Language Processing tasks such as tokenization, part-of-speech tagging, and dependency parsing for multiple languages. | 554 |
utcompling/texnlp | Develops tools and algorithms for natural language processing tasks using Hidden Markov Models and Maximum Entropy Markov Models. | 14 |
zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,041 |
jd-aig/nlp_baai | A collection of natural language processing models and tools for collaboration on a joint project between BAAI and JDAI. | 252 |
kimtaro/ve | A linguistic framework for natural language processing tasks. | 216 |
chartbeat-labs/textacy | A Python library providing a range of natural language processing tasks and utilities | 2,217 |
vseloved/cl-nlp | A comprehensive Common Lisp toolkit for natural language processing tasks. | 222 |
pprett/nut | A toolkit for natural language understanding and machine learning | 118 |