nlp-architect 0.5

Intel AI Lab's open-source NLP and NLU research library

A Deep Learning NLP/NLU library by Intel® AI Lab

Overview | Models | Installation | Examples | Documentation | Tutorials | Contributing

NLP Architect is an open source Python library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing and Natural Language Understanding neural network.

Overview

NLP Architect is an NLP library designed to be flexible, easy to extend, allow for easy and rapid integration of NLP models in applications and to showcase optimized models.

Features:

• Core NLP models used in many NLP tasks and useful in many NLP applications

• Novel NLU models showcasing novel topologies and techniques

• Optimized NLP/NLU models showcasing different optimization algorithms on neural NLP/NLU models

• Model-oriented design:

  • Train and run models from command-line.
  • API for using models for inference in python.
  • Procedures to define custom processes for training, inference or anything related to processing.
  • CLI sub-system for running procedures

• Based on optimized Deep Learning frameworks:

  • TensorFlow
  • PyTorch
  • Intel-Optimized TensorFlow with MKL-DNN
  • Dynet

• Essential utilities for working with NLP models - Text/String pre-processing, IO, data-manipulation, metrics, embeddings.

• Plug-able REST API server to serve models via REST API

Installing NLP Architect

We recommend to install NLP Architect in a new python environment, to use python 3.6+ with up-to-date pip, setuptools and h5py.

Install using pip

Includes only core library (without examples/ directory)

pip install nlp-architect

Install from source (Github)

Includes core library and all content (example scripts, datasets, tutorials)

Clone repository

git clone https://github.com/NervanaSystems/nlp-architect.git
cd nlp-architect

Install (in develop mode)

pip install -e .

Further installation options

Refer to our full installation instructions page on our website for complete details on how to install NLP Architect and other backend installations such as MKL-DNN or GPU backends. Users can install any deep learning backends manually before/after they install NLP Architect.

Models

NLP models that provide best (or near) in class performance:

• Word chunking
• Named Entity Recognition
• Dependency parsing
• Intent Extraction
• Sentiment classification
• Language models
• Transformers (for NLP tasks)

Natural Language Understanding (NLU) models that address semantic understanding:

• Aspect Based Sentiment Analysis (ABSA)
• Joint intent detection and slot tagging
• Noun phrase embedding representation (NP2Vec)
• Most common word sense detection
• Relation identification
• Cross document coreference
• Noun phrase semantic segmentation

Optimizing NLP/NLU models and misc. optimization techniques:

• Quantized BERT (8bit)
• Knowledge Distillation using Transformers
• Sparse and Quantized Neural Machine Translation (GNMT)

Solutions (End-to-end applications) using one or more models:

• Term Set expansion - uses the included word chunker as a noun phrase extractor and NP2Vec to create semantic term sets
• Topics and trend analysis - analyzing trending phrases in temporal corpora
• Aspect Based Sentiment Analysis (ABSA)

Documentation

Full library documentation of NLP models, algorithms, solutions and instructions on how to run each model can be found on our website.

NLP Architect library design philosophy

NLP Architect is a model-oriented library designed to showcase novel and different neural network optimizations. The library contains NLP/NLU related models per task, different neural network topologies (which are used in models), procedures for simplifying workflows in the library, pre-defined data processors and dataset loaders and misc utilities. The library is designed to be a tool for model development: data pre-process, build model, train, validate, infer, save or load a model.

The main design guidelines are:

• Deep Learning framework agnostic
• NLP/NLU models per task
• Different topologies used in models
• Showcase End-to-End applications (Solutions) utilizing one or more NLP Architect model
• Generic dataset loaders, textual data processing utilities, and miscellaneous utilities that support NLP model development (loaders, text processors, io, metrics, etc.)
• Procedures for defining processes for training, inference, optimization or any kind of elaborate script.
• Pythonic API for using models for inference
• REST API servers with ability to serve trained models via HTTP
• Extensive model documentation and tutorials

Note

NLP Architect is an active space of research and development; Throughout future releases new models, solutions, topologies and framework additions and changes will be made. We aim to make sure all models run with Python 3.6+. We encourage researchers and developers to contribute their work into the library.

Citing

If you use NLP Architect in your research, please use the following citation:

@misc{izsak_peter_2018_1477518, title = {NLP Architect by Intel AI Lab}, month = nov, year = 2018, doi = {10.5281/zenodo.1477518}, url = {https://doi.org/10.5281/zenodo.1477518} }

Disclaimer

The NLP Architect is released as reference code for research purposes. It is not an official Intel product, and the level of quality and support may not be as expected from an official product. NLP Architect is intended to be used locally and has not been designed, developed or evaluated for production usage or web-deployment. Additional algorithms and environments are planned to be added to the framework. Feedback and contributions from the open source and NLP research communities are more than welcome.

Contact

Contact the NLP Architect development team through Github issues or email: [e-mail]