malaya 0.7.5.2

Natural-Language-Toolkit for bahasa Malaysia, powered by Deep Learning.

Malaya

Natural-Language-Toolkit for bahasa Malaysia, powered by Deep Learning Tensorflow.

Features

• Entities Recognition, using latest state-of-art CRF deep learning model.

• Language Detection, using Character-wise eXtreme Gradient Boosting to distinguish Malay, English, and Indonesian.

• Normalizer, using local Malaysia NLP researches to normalize any bahasa texts.

• Num2Word

• Part-of-Speech Recognition, using latest state-of-art CRF deep learning model.

• Sentiment Analysis, from BERT, Fast-Text, Dynamic-Memory Network, Attention to build deep sentiment analysis models.

• Spell Correction, using local Malaysia NLP researches to auto-correct any bahasa words.

• Stemmer

• Summarization, using skip-thought state-of-art to give precise summarization.

• Topic Modelling

• Topic and Influencers Analysis, using deep and machine learning models to understand topics and Influencers similarity in sentences.

• Toxicity Analysis, from Fast-Text, Stacking, Entity-Network to do multi-label classification.

• Word2Vec

Installation

The latest release of Malaya can be installed using pip,

pip install malaya

Also, if want to install GPU version, simply,

pip install malaya-gpu

Documentation

All the documentations moved to Malaya Wiki.

Contributors

• Husein Zolkepli - Initial work - huseinzol05

• Sani - build PIP package - khursani8