Google Open-Sources AI for Using Tabular Data to Answer Natural Language Questions

2319

Google open-sourced Table Parser (TAPAS), a deep-learning system that can answer natural-language questions from tabular data. TAPAS was trained on 6.2 million tables extracted from Wikipedia and matches or exceeds state-of-the-art performance on several benchmarks. Co-creator Thomas Müller gave an overview of the work in a recent blog post.

Read More at InfoQ.com