Have Researchers Taught AI How To Recognize And Understand Language?

The most widely tested model, so far, is called Embeddings from Language Models, or ELMo. When it was released by the Allen Institute this spring, ELMo swiftly toppled previous bests on a variety of challenging tasks—like reading comprehension, where an AI answers SAT-style questions about a passage, and sentiment analysis. In a field where progress tends to be incremental, adding ELMo improved results by as much as 25 percent.