When communicating, context is king. A breakthrough in modelling context in human communication could make computers better conversationalists, according to cognitive scientists at Stanford University.
“[Michael] Frank, [head of Stanford University’s Language and Cognition Lab] and colleague Noah Goodman, also a cognitive scientist from Stanford, have developed a mathematical encoding of what they call “common knowledge” and “informativeness” in human conversation. “We have a vastly powerful predictive model of the world,” says Goodman. “When somebody goes to understand a statement that somebody else has made, they’re making the best guess about the meaning of that statement, incorporating all these factors like informativeness and context.”
By “putting numbers to” a theory of communication that dates back to the 1960s, they have come up with a model that not only describes part of the mutual understanding shared between human speakers, but also lays the groundwork for the next generation of our AI interlocutors, from pocket voice assistants like Apple’s Siri and Android’s Iris to automated customer-service bots. “We’ve created a formalism for trying to predict what speakers are talking about and shown that it makes pretty good predictions,” says Frank. But the developers of Iris, for instance, also confirm that context-based understanding will give the edge in their field.”
We are an international experience design consultancy helping companies and organisations to innovate their products, services and processes by putting people and their experiences first.
Reposted from Medium Beyond the engineering challenge of creating cars that drive themselves lies the social challenge. Before autonomous cars are ready to navigate our roads, they must be able to navigate the vastly more complicated nuances of human behaviors and interactions — from that friendly nod that says “You first” at a four-way stop, to the […]
Ripostato da Medium – English version Il mondo del fashion sta diventando sempre di più digitale — e non si tratta solo di dispositivi da indossare, ma anche e soprattutto di abbigliamento, realizzato con tessuti in cui sono effettivamente integrati dei sensori in grado di misurare e monitorare il corpo di chi li veste. Dato che la […]
Reposted from Medium – Versione italiana The world of fashion is becoming increasingly digital — and not just wearable devices, but with clothing made from fabrics that actually integrate sensors and technology that can monitor and measure the wearer. As fashion starts to go beyond outward appearance, fashion designers need to broaden their skillsets, to make sure […]
It’s that time of year again – Milan’s don’t-miss event for the design community is here. If you’re looking to get inspired at Milan Design Week, then check out our top picks for the latest edition, from Experientia’s designers, strategists and partners. Milan might be best known for its busy streets, traditional cafés and world […]
Following the 2016 Smart Innovation Award at “FIMBACTE Trophées du Cadre de vie”, the CITYOPT project has once again been recognized, this time in the prestigious French design competition: “Observeur du Design 2017”, in the Service Design category. In June 2016, CITYOPT won the first stage of the Observeur du Design. Now the project has […]
Last month Putting People First announced the upcoming conference on design & sustainable innovation for smart cities in Nice France. Meanwhile we are pleased to announce the full event agenda (see below). This event will feature professionals from leading research institutes and industry gathering to present key initiatives which combine Energy Efficiency and Service Design […]