Currently with R. Speer, J. Lowry-Duda, R. Beaudoin, and J. Alonso
ConceptNet is a freely-available semantic network, designed to help computers understand the meanings of words that people use. ConceptNet has been used in thousands of academic papers and several commercial companies. New research comes out constantly using ConceptNet. We have a knowledge graph in every language that has a Wikipedia and we turn it into word embeddings using a technique called retrofitting to make Numberbatch.
Why a giant knowledge graph of world knowledge? Language in any form requires understanding connections among words, concepts, phrases and thoughts. Many of the problems we face today in artificial intelligence depend in some way on understanding this network of relationships, which represent the facts that each of us knows about the world and how words relate to one another. When people communicate with each other, their conversation relies on many basic, unspoken assumptions, and they often learn the basis behind these assumptions long before they can write at all. Only traces of these assumptions are found in corpora.