Counting 3,039 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Aug. 16, 2018
Apr. 4, 2018

GluonNLP: Your Choice of Deep Learning for NLP

GluonNLP is a toolkit that enables easy text preprocessing, datasets loading and neural models building to help you speed up your Natural Language Processing (NLP) research.


Make sure you have Python 2.7 or Python 3.6 and recent version of MXNet. You can install MXNet and GluonNLP using pip:

pip install --pre --upgrade mxnet
pip install gluonnlp

Docs đź“–

GluonNLP documentation is available at our website.


For questions and comments, please visit our forum (and Chinese version). For bug reports, please submit Github issues.

How to Contribute

GluonNLP has been developed by community members. Everyone is more than welcome to contribute. We together can make the GluonNLP better and more user-friendly to more users.

Read our contributing guide to get to know about our development procedure, how to propose bug fixes and improvements, as well as how to build and test your changes to GluonNLP.

Join our contributors.


Check out how to use GluonNLP for your own research or projects.

If you are new to Gluon, please check out our 60-minute crash course.

For getting started quickly, refer to notebook runnable examples at Examples.

For advanced examples, check out our Scripts.

For experienced users, check out our API Notes.

Quick Start Guide

Dataset Loading

Load the Wikitext-2 dataset, for example:

>>> import gluonnlp as nlp
>>> train ='train')
>>> train[0][0:5]
['=', 'Valkyria', 'Chronicles', 'III', '=']

Vocabulary Construction

Build vocabulary based on the above dataset, for example:

>>> vocab = nlp.Vocab([0]))
>>> vocab
Vocab(size=33280, unk="<unk>", reserved="['<pad>', '<bos>', '<eos>']")

Neural Models Building

From the models package, apply a Standard RNN language model to the above dataset:

>>> model = nlp.model.language_model.StandardRNN('lstm', len(vocab),
...                                              200, 200, 2, 0.5, True)
>>> model
  (embedding): HybridSequential(
    (0): Embedding(33280 -> 200, float32)
    (1): Dropout(p = 0.5, axes=())
  (encoder): LSTM(200 -> 200.0, TNC, num_layers=2, dropout=0.5)
  (decoder): HybridSequential(
    (0): Dense(200 -> 33280, linear)

Word Embeddings Loading

For example, load a GloVe word embedding, one of the state-of-the-art English word embeddings:

>>> glove = nlp.embedding.create('glove', source='glove.6B.50d')
# Obtain vectors for 'baby' in the GloVe word embedding
>>> type(glove['baby'])
<class 'mxnet.ndarray.ndarray.NDArray'>
>>> glove['baby'].shape

Latest Releases
 Jul. 24 2018
 Jul. 19 2018
 Jul. 11 2018
 Jun. 12 2018
 Jun. 12 2018