Facebook announces open-source NLP modelling framework PyText

Facebook AI Research (FAIR) announces the open-source NLP modelling framework PyText. PyText is a deep learning NLP modelling framework built on PyTorch. PyText blurs the line between experimentation and large-scale deployment by providing a simple and extensible interface and abstraction for model components and the ability to reason with PyTorch’s Caffe2 execution engine export model. Its pre-training model includes text classification, sequence labelling and so on.

PyTorch is a unified framework that shortens the path from research to production, while PyTorch-based PyText focuses on meeting the specific needs of NLP modelling.

Image: code.fb

Core PyText features:

• Production ready models for various NLP/NLU tasks:
  • Text classifiers
    • Yoon Kim (2014): Convolutional Neural Networks for Sentence Classification
    • Lin et al. (2017): A Structured Self-attentive Sentence Embedding
  • Sequence taggers
    • Lample et al. (2016): Neural Architectures for Named Entity Recognition
  • Joint intent-slot model
    • Zhang et al. (2016): A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding
  • Contextual intent-slot models
• Distributed-training support built on the new C10d backend in PyTorch 1.0
• Extensible components that allows easy creation of new models and tasks
• Reference implementation and a pretrained model for the paper: Gupta et al. (2018): Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
• Ensemble training support

Link to this project here.