Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Watch a conference presentation from Yale Professor Dragomir Radev at INSAIT 2022 exploring the challenges and advancements in natural language interfaces for relational databases. Dive into the complexities of translating human language into database queries and back, with a focus on three key datasets developed through the Yale Spider project. Learn about the Spider collection containing over 10,000 natural language questions and nearly 6,000 corresponding database queries across 138 domains, the SParC dataset featuring 4,298 sequential question-query pairs, and the CoSQL dataset comprising 3,000 dialogues with 30,000 conversation turns. Discover GraPPa, an innovative pre-training approach that achieves state-of-the-art performance in table semantic parsing by learning compositional patterns in combined textual and tabular data. Explore recent developments in text generation from hybrid inputs, combining structured and unstructured text formats.
