Be Cool with Boole

May 10, 2021

How often have you turned to a search engine to answer a question? You know the answer is on the tip of your tongue, but you cannot remember anything about it. Take that back, you do remember things about the answer, that is you know “what it is not.” For example, you are trying to remember the name of 1980s transforming robots but they are not Hasbro Transformers. Usually you could use the Boolean operator “not” in the search term, but that does not yield results.

Thankfully Tech Xplore explains that negative search options are on their way in the article: “New Approach Enables Search Engines To Describe Objects With Negative Statements.” Search engines and other computer programs use knowledge bases to answer user questions. The information must be structured in order for it to be discovered. Most information in knowledge bases use positive statements or statements that describe something true. Negative statements are not although they contain valuable information. They are to used, because there is an infinite number of negative statements; therefore impossible to structure every one.

Simon Razniewski of the Saarbücken Max-Planck-Institute for Informatics and his research team created a method to generate negative statements for knowledge bases in different applications. It works by:

“Using Steven Hawking as an example, the novel approach works as follows: First, several reference cases are identified that share a prominent property with the search object. In the example: physicists. The researchers call these comparison cases “peers.” Now, based on the “peers,” a selection of positive assumptions about the initial entity is generated. Since the physicists Albert Einstein and Richard Feynman won the Nobel Prize, the assumption Steven Hawking won the Nobel Prize could be made. Then, the new assumptions are matched with existing information in the knowledge base about the initial entity. If a statement applies to a “peer” but not to the search object, the researchers conclude that it is a negative statement for the search object—i.e., Steven Hawking never won the Nobel Prize. To evaluate the significance of the negative statements generated, they are sorted using various parameters, for example, how often they occurred in the peer group.”

The research team uses recommender systems like those in search engines or on commerce Web sites. They hope to refine the system to identify nuanced negative statements and implicit negative statements. Using negative statements will make search engines more intuitive and the research crosses over into the realms of NLP and AI. Boolean operators could become more obsolete.

Boolean may be back!

Whitney Grace, May 10, 2021

Comments

Got something to say?





  • Archives

  • Recent Posts

  • Meta