The latest Cloudera Fast Forward Labs research report and prototype, Multi-Task Learning, introduces a novel approach to problem solving with machine learning that is unlocking new possibilities across industries, from finance and media to healthcare and agriculture.
Unlike single-task learning, multi-task learning allows machine learning algorithms to master more than one task, benefiting from the relationships between tasks and resulting in more accurate models that generalize better to new tasks. And, because these models can handle more complex challenges that involve richer representations of reality, they're delivering new scientific and commercially valuable insights across industries.
Newsie, the prototype that accompanies this report, classifies news articles into categories (e.g., news, sports, entertainment). It was trained using multi-task learning to correctly classify buttoned-up broadsheet articles ("Task 1") and more sensationalist tabloid ones ("Task 2").
Newsie's article view shows how the model arrives at the classification on a word-by-word level. From surrounding sentences to place of publication, context changes word meaning. Enabled by multi-task learning, Newsie provides users with a window into the differences in coverage and language use across the buttoned-up and sensationalist press; it puts current news into perspective.