We’ve already seen how awkward computers will be once they speak like humans, but researchers from North Carolina State and Georgia Tech have now developed a program which may assist you show them how it’s done. Their approach, outlined in a recently published paper, would allow developers to create natural language generation (NLG) systems twice as fast as currently possible. NLG technology is utilized in a wide selection of applications (including games and customer support centers), but producing these systems has traditionally required developers to go into massive amounts of knowledge, vocabulary and templates — rules that computers use to develop coherent sentences. Lead author Karthik Narayan and his team, however, have created a program able to learning methods to use these templates by itself, thereby requiring developers to input only basic information regarding any given topic of conversation. Because it learns easy methods to speak, the software may make automatic suggestions about which information must be added to its database, in keeping with the conversation to hand. Narayan and his colleagues will present their study at this year’s Artificial Intelligence and Interactive Digital Entertainment conference in October, but you are able to dig through it for yourself, on the link below.
Sprint launches New Ventures arm, adapts ID and Zone apps for foreign markets
Proton and Yes team as much as offer Malaysia’s first 4G-connected car, promise more to return
