The meaning that humans associate with words, phrases, sentences and stories is grounded in human experience, writes David Ferrucci, lead researcher for IBM's Watson project.
When computers try to interpret human language, they simply see a long series of 0s and 1s, which are difficult to relate to the overall human experience. The challenge for natural-language processing technologies is to program computers to do a better job of understanding the context of human language, Ferrucci says.
Computers struggle with the fact that so much of human knowledge is in natural-language content. In order to be useful tools, computers need to be able to provide precise answers with meaningful justifications, Ferrucci notes.
Computers should communicate in human terms instead of forcing humans to communicate in computer languages. "If we could program computers to more precisely interpret natural language the way we do, then we could leverage their speed to give us more precise and better justified responses based on enormous resources of knowledge that are simply out of our reach," Ferrucci says.
View Full Article
No entries found