Minerva: Solving Quantitative Reasoning Problems with Language Models

Posted by Ethan Dyer and Guy Gur-Ari, Research Scientists, Google Research, Blueshift Team

Language models have demonstrated remarkable performance on a variety of natural language tasks — indeed, a general lesson from many works, including BERT, GPT-3, Gopher, and PaLM, has been that neural networks trained on diverse data at large scale in an unsupervised way can perform well on a variety of tasks.

Quantitative reasoning is one area in which language models still fall far …

deep learning education language language models minerva natural language processing reasoning self-supervised learning