Welcome to Malaya’s documentation!

logo

Pypi version Python3 version MIT License Documentation Build status


Malaya is a Natural-Language-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow.

Documentation

Proper documentation is available at https://malaya.readthedocs.io/

Installing from the PyPI

CPU version

$ pip install malaya

GPU version

$ pip install malaya-gpu

Only Python 3.6.x and above and Tensorflow 1.X are supported.

Features

  • Emotion Analysis

    From BERT, Fast-Text, Dynamic-Memory Network, Sparse Tensorflow, Attention Neural Network to build deep emotion analysis models.

  • Entities Recognition

    Latest state-of-art CRF deep learning models to do Naming Entity Recognition.

  • Language Detection

    using Multinomial, SGD, XGB, Fast-text N-grams deep learning to distinguish Malay, English, and Indonesian.

  • Normalizer

    using local Malaysia NLP researches to normalize any bahasa texts.

  • Num2Word

    Convert from numbers to cardinal or ordinal representation.

  • Part-of-Speech Recognition

    Latest state-of-art CRF deep learning models to do Naming Entity Recognition.

  • Dependency Parsing

    Latest state-of-art CRF deep learning models to do analyzes the grammatical structure of a sentence, establishing relationships between words.

  • ELMO (biLM)

    Provide pretrained bahasa wikipedia and bahasa news ELMO, with easy interface and visualization.

  • Sentiment Analysis

    From BERT, Fast-Text, Dynamic-Memory Network, Sparse Tensorflow, Attention Neural Network to build deep sentiment analysis models.

  • Spell Correction

    Using local Malaysia NLP researches to auto-correct any bahasa words.

  • Stemmer

  • Subjectivity Analysis

    From BERT, Fast-Text, Dynamic-Memory Network, Sparse Tensorflow, Attention Neural Network to build deep subjectivity analysis models.

  • Summarization

    Using skip-thought with attention state-of-art to give precise unsupervised summarization.

  • Topic Modelling

    Provide LDA2Vec, LDA, NMF and LSA interface for easy topic modelling with topics visualization.

  • Toxicity Analysis

    From BERT, Fast-Text, Dynamic-Memory Network, Attention Neural Network to build deep toxicity analysis models.

  • Word2Vec

    Provide pretrained bahasa wikipedia and bahasa news Word2Vec, with easy interface and visualization.

  • Fast-text

    Provide pretrained bahasa wikipedia Fast-text, with easy interface and visualization.

License

License

Contents: