The Fifth Elephant round the year submissions for 2019

Submit a talk on data, data science, analytics, business intelligence, data engineering and ML engineering

Participate Propose a session

Interpretable NLP Models

Submitted by Logesh kumar (@infinitylogesh) on Friday, 31 May 2019

Session type: Tutorial


Deep learning models are always known to be a black box and lacks interpretability compared to traditional machine learning models. So,There is alway a hesitation in adopting deep learning models in user facing applications (especially medical applications). Recent progress in NLP with the advent of Attention based models , LIME and other techniques have helped to solve this. I would like to walkthough each of the techniques and share my experience in deploying explainable models in production.


  1. Brief introduction on the importance of interpretability
  2. Introduction to different interpretabilty techniques
    2.1 Attention based models
    2.2 LIME
    2.3 Extraction based models
    2.4 other techniques
  3. Demo of the techniques.


No specific requirements.

Speaker bio

I am Data scientist with a focus on NLP. I have first hand experience of facing problems occuring because of non intrepretability of deep learning models and also I have experience in deploying deep learning based NLP models from protype to production.


  • Abhishek Balaji (@booleanbalaji) Reviewer 19 days ago

    Hi Logesh,

    Thank you for submitting a proposal. We need to see detailed slides and a preview video to evaluate your proposal. Your slides must cover the following:

    • Problem statement/context, which the audience can relate to and understand. The problem statement has to be a problem (based on this context) that can be generalized for all.
    • What were the tools/frameworks available in the market to solve this problem? How did you evaluate these, and what metrics did you use for the evaluation? Why did you pick the option that you did?
    • Explain how the situation was before the solution you picked/built and how it changed after implementing the solution you picked and built? Show before-after scenario comparisons & metrics.
    • What compromises/trade-offs did you have to make in this process?
    • What is the one takeaway that you want participants to go back with at the end of this talk? What is it that participants should learn/be cautious about when solving similar problems?

    We need your updated slides and preview video by Jun 10, 2019 to evaluate your proposal. If we do not receive an update, we’d be moving your proposal for evaluation under a future event.

  • Abhishek Balaji (@booleanbalaji) Reviewer a day ago

    Marking as rejected since proposer hasnt responded to comments.

Login with Twitter or Google to leave a comment