A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Tensorflow
implementation of the GNMT model with sparsity and quantization operations integrated.tf.keras
and added CNN-character based feature extractors and improved accuracy of all models.Tensorflow
based CRF layer.tf.keras
.Tensorflow
.nlp_architect
- a simple command initiator to handle maintenance tasks, see nlp_architect -h
for the list of commands.Tensorflow
Tensorflow
Keras
Tensorflow
Tensorflow
tf.keras
and use state-of-art modeltf.keras
CONLL2000
, Amazon_Review
, PTB
, Fasttext
, Wikitext-103
and Wikipedia-dump
dataset loaders.hug
, new streamlined the UI and improved documentation. See updated documentation for further details.spaCy
pipelineJupyter
notebook tutorials using NLP Architect modelsThe current version of NLP Architect includes these features that we found interesting from both research perspectives and practical applications: