Computers are finally able to solve word problems and bring our dreams to reality
When I was first introduced to the computers years ago, I wasn't impressed. All I wanted to know whether the machine would provide me answers to the questions I directly typed in. The answer then, was 'no'; but engineers at MIT have turned it into a 'yes'. A team of researchers at MIT's Computer Science and Artificial Intelligence Laboratory along with a team from University of Washington has developed complex algorithms that are capable of solving word problems. As of now, the system can correctly answer the algebra problems and is likely to evolve to solve physics and chemistry problems as well. You don't have to break down the question into parts or make the computer understand it; the computer does it all by itself.
Illustration: Jose-Luis Olivares/MIT
The system has been developed by Nate Kushman along with Regina Barzilay and team. In order to make the computer understand the word problems, the researchers relied on two existing computational tools - Macsyma and a sentence parser. Macsyma identifies the structure of the word problem and converts it into a template. The sentence parser ensures the meanings of the words are correctly put into context by relating them. For example, if the system encounters phrase 'react with', it gets a hint that the problem is related to Chemistry. If the question has words like 'costs' or 'price', the system thinks that the problem is likely to involve money related calculations.
The researchers have put sanity checks into the system, so that the outputs aren't bizarre. For example, if the problem is about calculating height of an object, then the system won't output a negative number. The applications of such a system are numerous. Right from using it in search engines to to solving common geometry or physics problems; the applications are unlimited. Do let us know your thoughts on the system.
Source: #-Link-Snipped-#
Illustration: Jose-Luis Olivares/MIT
The system has been developed by Nate Kushman along with Regina Barzilay and team. In order to make the computer understand the word problems, the researchers relied on two existing computational tools - Macsyma and a sentence parser. Macsyma identifies the structure of the word problem and converts it into a template. The sentence parser ensures the meanings of the words are correctly put into context by relating them. For example, if the system encounters phrase 'react with', it gets a hint that the problem is related to Chemistry. If the question has words like 'costs' or 'price', the system thinks that the problem is likely to involve money related calculations.
The researchers have put sanity checks into the system, so that the outputs aren't bizarre. For example, if the problem is about calculating height of an object, then the system won't output a negative number. The applications of such a system are numerous. Right from using it in search engines to to solving common geometry or physics problems; the applications are unlimited. Do let us know your thoughts on the system.
Source: #-Link-Snipped-#
0
