Quick start

Installation

Make sure to use Python 3.6+ and a virtual environment.

Using pip

pip install nlp_architect

From source

git clone https://github.com/NervanaSystems/nlp-architect.git
cd nlp-architect
pip install -e .  # install in development mode

Note

For specific installation of backends of Tensorflow or PyTorch (CPU/MKL/GPU) we recommend installing NLP Architect and then installing the desired package of framework.

Running Examples and Solutions

To run provided examples and solutions please install the library with [all] flag which will install extra packages required. (requires installation from source)

pip install .[all]

Usage

NLP Architect has the following packages:

Package Description
nlp_architect.api Model API interfaces
nlp_architect.common Common packages
nlp_architect.cli Command line module
nlp_architect.data Datasets, loaders and data processors
nlp_architect.models NLP, NLU and End-to-End models
nlp_architect.nn Topology related models and additions (per framework)
nlp_architect.pipelines End-to-end NLP apps
nlp_architect.procedures Procedure scripts
nlp_architect.utils Misc. I/O, metric, pre-processing and text utilities

CLI

NLP Architect comes with a CLI application that helps users run procedures and processes from the library.

Warning

The CLI is in development and some functionality is not complete and will be added in future versions

NLP Architect commands:

nlp-train       Train a model from the library
nlp-inference   Run a model from the library

Use nlp-train/inference -h for per command usage instructions.