Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Computer learns language by playing games

13.07.2011
By basing its strategies on the text of a manual, a computer infers the meanings of words without human supervision.

Computers are great at treating words as data: Word-processing programs let you rearrange and format text however you like, and search engines can quickly find a word anywhere on the Web. But what would it mean for a computer to actually understand the meaning of a sentence written in ordinary English — or French, or Urdu, or Mandarin?

One test might be whether the computer could analyze and follow a set of instructions for an unfamiliar task. And indeed, in the last few years, researchers at MIT’s Computer Science and Artificial Intelligence Lab have begun designing machine-learning systems that do exactly that, with surprisingly good results.

In 2009, at the annual meeting of the Association for Computational Linguistics (ACL), researchers in the lab of Regina Barzilay, associate professor of computer science and electrical engineering, took the best-paper award for a system that generated scripts for installing a piece of software on a Windows computer by reviewing instructions posted on Microsoft’s help site. At this year’s ACL meeting, Barzilay, her graduate student S. R. K. Branavan and David Silver of University College London applied a similar approach to a more complicated problem: learning to play “Civilization,” a computer game in which the player guides the development of a city into an empire across centuries of human history. When the researchers augmented a machine-learning system so that it could use a player’s manual to guide the development of a game-playing strategy, its rate of victory jumped from 46 percent to 79 percent.

Starting from scratch

“Games are used as a test bed for artificial-intelligence techniques simply because of their complexity,” says Branavan, who was first author on both ACL papers. “Every action that you take in the game doesn’t have a predetermined outcome, because the game or the opponent can randomly react to what you do. So you need a technique that can handle very complex scenarios that react in potentially random ways.”

Moreover, Barzilay says, game manuals have “very open text. They don’t tell you how to win. They just give you very general advice and suggestions, and you have to figure out a lot of other things on your own.” Relative to an application like the software-installing program, Branavan explains, games are “another step closer to the real world.”

The extraordinary thing about Barzilay and Branavan’s system is that it begins with virtually no prior knowledge about the task it’s intended to perform or the language in which the instructions are written. It has a list of actions it can take, like right-clicks or left-clicks, or moving the cursor; it has access to the information displayed on-screen; and it has some way of gauging its success, like whether the software has been installed or whether it wins the game. But it doesn’t know what actions correspond to what words in the instruction set, and it doesn’t know what the objects in the game world represent.

So initially, its behavior is almost totally random. But as it takes various actions, different words appear on screen, and it can look for instances of those words in the instruction set. It can also search the surrounding text for associated words, and develop hypotheses about what actions those words correspond to. Hypotheses that consistently lead to good results are given greater credence, while those that consistently lead to bad results are discarded.

Proof of concept

In the case of software installation, the system was able to reproduce 80 percent of the steps that a human reading the same instructions would execute. In the case of the computer game, it won 79 percent of the games it played, while a version that didn't rely on the written instructions won only 46 percent. The researchers also tested a more-sophisticated machine-learning algorithm that eschewed textual input but used additional techniques to improve its performance. Even that algorithm won only 62 percent of its games.

“If you’d asked me beforehand if I thought we could do this yet, I’d have said no,” says Eugene Charniak, University Professor of Computer Science at Brown University. “You are building something where you have very little information about the domain, but you get clues from the domain itself.”

Charniak points out that when the MIT researchers presented their work at the ACL meeting, some members of the audience argued that more sophisticated machine-learning systems would have performed better than the ones to which the researchers compared their system. But, Charniak adds, “it’s not completely clear to me that that’s really relevant. Who cares? The important point is that this was able to extract useful information from the manual, and that’s what we care about.”

Most computer games as complex as “Civilization” include algorithms that allow players to play against the computer, rather than against other people; the games’ programmers have to develop the strategies for the computer to follow and write the code that executes them. Barzilay and Branavan say that, in the near term, their system could make that job much easier, automatically creating algorithms that perform better than the hand-designed ones.

But the main purpose of the project, which was supported by the National Science Foundation, was to demonstrate that computer systems that learn the meanings of words through exploratory interaction with their environments are a promising subject for further research. And indeed, Barzilay and her students have begun to adapt their meaning-inferring algorithms to work with robotic systems.

Caroline McCall | EurekAlert!
Further information:
http://www.mit.edu

More articles from Interdisciplinary Research:

nachricht Bergamotene - alluring and lethal for Manduca sexta
21.04.2017 | Max-Planck-Institut für chemische Ökologie

nachricht How to color a lizard: From biology to mathematics
13.04.2017 | Université de Genève

All articles from Interdisciplinary Research >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Can the immune system be boosted against Staphylococcus aureus by delivery of messenger RNA?

Staphylococcus aureus is a feared pathogen (MRSA, multi-resistant S. aureus) due to frequent resistances against many antibiotics, especially in hospital infections. Researchers at the Paul-Ehrlich-Institut have identified immunological processes that prevent a successful immune response directed against the pathogenic agent. The delivery of bacterial proteins with RNA adjuvant or messenger RNA (mRNA) into immune cells allows the re-direction of the immune response towards an active defense against S. aureus. This could be of significant importance for the development of an effective vaccine. PLOS Pathogens has published these research results online on 25 May 2017.

Staphylococcus aureus (S. aureus) is a bacterium that colonizes by far more than half of the skin and the mucosa of adults, usually without causing infections....

Im Focus: A quantum walk of photons

Physicists from the University of Würzburg are capable of generating identical looking single light particles at the push of a button. Two new studies now demonstrate the potential this method holds.

The quantum computer has fuelled the imagination of scientists for decades: It is based on fundamentally different phenomena than a conventional computer....

Im Focus: Turmoil in sluggish electrons’ existence

An international team of physicists has monitored the scattering behaviour of electrons in a non-conducting material in real-time. Their insights could be beneficial for radiotherapy.

We can refer to electrons in non-conducting materials as ‘sluggish’. Typically, they remain fixed in a location, deep inside an atomic composite. It is hence...

Im Focus: Wafer-thin Magnetic Materials Developed for Future Quantum Technologies

Two-dimensional magnetic structures are regarded as a promising material for new types of data storage, since the magnetic properties of individual molecular building blocks can be investigated and modified. For the first time, researchers have now produced a wafer-thin ferrimagnet, in which molecules with different magnetic centers arrange themselves on a gold surface to form a checkerboard pattern. Scientists at the Swiss Nanoscience Institute at the University of Basel and the Paul Scherrer Institute published their findings in the journal Nature Communications.

Ferrimagnets are composed of two centers which are magnetized at different strengths and point in opposing directions. Two-dimensional, quasi-flat ferrimagnets...

Im Focus: World's thinnest hologram paves path to new 3-D world

Nano-hologram paves way for integration of 3-D holography into everyday electronics

An Australian-Chinese research team has created the world's thinnest hologram, paving the way towards the integration of 3D holography into everyday...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

Marine Conservation: IASS Contributes to UN Ocean Conference in New York on 5-9 June

24.05.2017 | Event News

AWK Aachen Machine Tool Colloquium 2017: Internet of Production for Agile Enterprises

23.05.2017 | Event News

Dortmund MST Conference presents Individualized Healthcare Solutions with micro and nanotechnology

22.05.2017 | Event News

 
Latest News

How herpesviruses win the footrace against the immune system

26.05.2017 | Life Sciences

Water forms 'spine of hydration' around DNA, group finds

26.05.2017 | Life Sciences

First Juno science results supported by University of Leicester's Jupiter 'forecast'

26.05.2017 | Physics and Astronomy

VideoLinks
B2B-VideoLinks
More VideoLinks >>>