Researchers from the Massachusetts Institute of Technology recently presented their new artificially intelligent system that can fill the information gap itself by surfing the Internet.
During the Association for Computational Linguistics’ Conference on Empirical Methods on Natural Language Processing, MIT researchers said the AI system has the ability to gather structured information from unstructured machine readable documents automatically.
Karthik Nasarimhan, one of the co-authors of the study, said that in order for them to do this, they employed a technique called reinforcement learning where the system learns through the notion of cumulative reward. This technique was based on behavioral psychology and is also used in swarm intelligence, game theory, and genetic algorithms among others.
According to Nasarimhan, the technique is necessary because there is a lot of contrasting information out which can cause uncertainty when the data is merged. Therefore, the system is given a reward every time it extracted data accurately. Through this, the AI learns to merge different data and information in an optima; manner possible.
To optimize te reward function of the system, the MIT researchers used deep-Q network, a machine learning technology that combines the power of Deep Neural Networks with Reinforcement Learning in the most scalable fashion possible.
After that they test the AI system by giving it two separate tasks. The first involved analyzing collective data on mass shooting while the other involved food contamination data. In both tasks, the AI fared 10 percent much better compared to trained human information extractors.
With this discovery, the scientists hope that through such type of system, it will be much easier to accelerate research tasks which could not only save time but also save lives. For example, doctors could use such system in aggregating their patient's medical history leading to a more improved quality of care given to the patient.
