At Cloudera Fast Forward, we routinely report on the latest and greatest in machine learning capabilities. Typically, our applied research culminates in a series of comprehensive reports released on a quarterly basis, along with a live webinar demonstrating the prototypes we build in conjunction with that research. But times they are a-changin’ and we’re experimenting with new formats for distributing our content! This time, instead of waiting until the prototype is finished and the report is polished, we thought it would be fun to invite you to join us while we build. Our posts will focus on the technical and practical aspects of building a QA system, including code samples. Because research of any kind is an inherently messy endeavor, be prepared for some ups and downs and maybe even a post or two about some tricky bugs we run across!

Posts

• Beyond SQuAD: How to Apply a Transformer QA Model to Your Data

  A look at how transfer learning can boost performance in specialized domains.

  Jul 22, 2020

• How to Maximize Retriever Performance on a More Natural Dataset

  Practical considerations for improving information retrieval in an IR QA system

  Jul 22, 2020

• Evaluating QA: the Retriever & the Full QA System

  A review of Information Retrieval and the role it plays in an IR QA system

  Jun 30, 2020

• Evaluating QA: Metrics, Predictions, and the Null Response

  A deep dive into computing QA predictions and when to tell BERT to zip it!

  Jun 9, 2020

• Building a QA System with BERT on Wikipedia

  A high-level code walk-through of an IR-based QA system with PyTorch and Hugging Face.

  May 19, 2020

• Intro to Automated Question Answering

  A gentle introuction to QA systems, our new applied research project

  Apr 28, 2020