Advancing Natural Language: Semantic Analysis using Semantic Parsing
Semantic parsing is the process of extracting meaning and intent from natural language text, which can often come from voice interactions. Well performed semantic parsing can also enable machines and software to learn by reading.
Traditional approaches to semantic parsing have been supervised: that is, humans provide a set of well-known input and output to the problem, and the machine "learns by example". But this has several problems, most obviously the way the machine will only learn as well as the examples teach--if you give the same software that performs great on the example set some natural language about a totally different topic, it wil often fail to perform adequately.
Unsupervised semantic parsing is relatively new but has been shown to outperform supervised approaches by three times on a regular basis. It relies on the key idea that the names of actions and object can be learned. This involves some self-learning--by providing a wide variety of examples about the same topic, the system is able to find similarities and infer that they're talking about the same subject, and learn based on it.
Newer semantic parsing systems are inherently probability-based. Meaning they understand what you're saying within a range of confidence. This isn't the same as hearing you wrong, as when you tell your phone to find the nearest steak house and it finds the nearest take out. That is bad voice recognition. This is where you tell Siri to find the nearest steak house and it thinks you means the nearest steak that can be bought near your house.
Book Promo
Secrets of the Big Data Revolution
Real-world success stories and roadmaps to get you there.
Commentary
Research Brief Creative Commons License
Please note that research briefs are provided by Applied Data Labs as a public record of ideas and techniques to put them into the public record and establish a commercial use date for protection against patent trolling. (For more information please see about Applied Data Labs.) However, no warranty is made as to their correctness and Applied Data Labs assumes no responsibility for their use. Commercial use of these ideas and techniques are allowed under the license linked to below.
This Research Brief by Applied Data Labs, Incorporated is licensed under a Creative Commons Attribution 3.0 Unported License.
The CIA admits to monitoring Twitter, Facebook, and blogs. This shouldn't surprise anyone, but the tools they’re using might be enough to get you to rethink posting anything personal or ever checking in...
This report is big business, it's important to remember it drives 100's of millions in corporate Business Intelligence(BI) spending, and has a hidden side to it. Although Gartner stays well away from saying it, there is a definite favorability for products from companies Gartner does business with. A quick look on Quora shows you exactly what that looks like: more time with business partners products and loosening of rules for inclusion.
You know about Big Data and its potential, how it creates greater understanding of our world, reduces waste and misuse of resources, and dramatically increases efficiency. The level of information available is growing like never before, and hiding in all that data are the insights, ideas, and explanations needed to reach that promised potential; it’s just waiting to be discovered, and there’s the problem.