Google Play icon

TensorFlow 2.0 Question Answering

Share
Posted October 30, 2019

“Why is the sky blue?”

This is a question an open-domain question answering (QA) system should be able to respond to. QA systems emulate how people look for information by reading the web to return answers to common questions. Machine learning can be used to improve the accuracy of these answers.

Human brain and cognitive abilities - artist's impression. Image credit: Max Pixel, CC0 Public Domain

Human brain and cognitive abilities – artist’s impression. Image credit: Max Pixel, CC0 Public Domain

Existing natural language models have been focused on extracting answers from a short paragraph rather than reading an entire page of content for proper context. As a result, the responses can be complicated or lengthy. A good answer will be both succinct and relevant.

The Competitor’s goal is to predict short and long answer responses to real questions about Wikipedia articles. The dataset is provided by Google’s Natural Questions but contains its own unique private test set.

About TensorFlow

TensorFlow is an open-source platform for machine learning. With TensorFlow 2.0, tf.keras is the preferred high-level API for TensorFlow, to make model-building easier and more intuitive.

Source: Kaggler

Featured news from related categories:

Technology Org App
Google Play icon
85,468 science & technology articles

Most Popular Articles

  1. New treatment may reverse celiac disease (October 22, 2019)
  2. The World's Energy Storage Powerhouse (November 1, 2019)
  3. "Helical Engine" Proposed by NASA Engineer could Reach 99% the Speed of Light. But could it, really? (October 17, 2019)
  4. Plastic waste may be headed for the microwave (October 18, 2019)
  5. Universe is a Sphere and Not Flat After All According to a New Research (November 7, 2019)

Follow us

Facebook   Twitter   Pinterest   Tumblr   RSS   Newsletter via Email