Despite constant advances and seemingly super-human performance on constrained domains, state-of-the-art models for NLP are imperfect. These imperfections, coupled with today’s advances being driven by (seemingly black-box) neural models, leave researchers and practitioners scratching their heads asking,why did my model make this prediction?

We present AllenNLP Interpret, a toolkit built on top of AllenNLP for interactive model interpretations. The toolkit makes it easy to apply gradient-basedsaliency mapsandadversarial attackstonew models, as well as developnew interpretation methods. AllenNLP interpret contains three components: a suite of interpretation techniques applicable to most models, APIs for developing new interpretation methods (e.g., APIs to obtain input gradients), and reusable front-end components for visualizing the interpretation results.

This page presents links to:

  • Paperdescribing the framework, the technical implementation details, and showing some example use cases.
  • Live demos for various models and tasks, such as
  • Tutorials for interpreting anymodel of your choice, and adddinga new interpretation method.
  • Codefor interpreting/attacking models and visualizing the results in the demo (e.g.,sentiment analysis).
  • Citation:

      Author={Eric Wallace and Jens Tuyls and Junlin Wang and Sanjay Subramanian
      and Matt Gardner and Sameer Singh},
      Booktitle={Empirical Methods in Natural Language Processing},
      Title={ {AllenNLP Interpret}: A Framework for Explaining Predictions of {NLP} Models}}

    Read More


    Please enter your comment!
    Please enter your name here