Crowd-Powered Intelligent Systems
نویسنده
چکیده
Human computation provides a new resource for creating intelligent systems that are able to go beyond the capabilities of fully-automated solutions. Currently, machines struggle in many real-world settings because problems can be almost entirely unconstrained and can vary greatly between instances. Solving problems such as natural language understanding require artificial intelligence to first reach human levels, a goal that is still very far off. Human computation can help bridge the gap between what computers can do and users’ ideal interactions, but is traditionally applied in an offline, batch-processing fashion. My work focuses on a new model of continuous, real-time crowdsourcing that enables interactive crowd-powered systems to be created.
منابع مشابه
"Is There Anything Else I Can Help You With?" Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent
Intelligent conversational assistants, such as Apple’s Siri, Microsoft’s Cortana, and Amazon’s Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address t...
متن کاملChorus: Letting the Crowd Speak with One Voice
Autonomous systems cannot yet reliably engage in an openended dialogue with users due the complexity of natural language processing, but online crowds present new opportunities to do so. We introduce Chorus, a system enabling real-time two-way natural language conversation between an end user and a single virtual agent powered by a distributed crowd of online humans. Chorus maintains consistent...
متن کاملEvorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time
Crowd-powered conversational assistants have been shown to be more robust than automated systems, but do so at the cost of higher response latency and monetary costs. A promising direction is to combine the two approaches for high quality, low latency, and low cost solutions. In this paper, we introduce Evorus, a crowd-powered conversational assistant built to automate itself over time by (i) a...
متن کاملOptimization techniques for human computation-enabled data processing systems
Crowdsourced labor markets make it possible to recruit large numbers of people to complete small tasks that are difficult to automate on computers. These marketplaces are increasingly widely used, with projections of over $1 billion being transferred between crowd employers and crowd workers by the end of 2012. While crowdsourcing enables forms of computation that artificial intelligence has no...
متن کاملScheduling Human Intelligence Tasks in Multi-Tenant Crowd-Powered Systems
Micro-task crowdsourcing has become a popular approach to e↵ectively tackle complex data management problems such as data linkage, missing values, or schema matching. However, the backend crowdsourced operators of crowd-powered systems typically yield higher latencies than the machineprocessable operators, this is mainly due to inherent efficiency di↵erences between humans and machines. This pr...
متن کامل