Learning language by playing games
System learns to play text-based computer game using only linguistic information.
MIT researchers have designed a computer system that learns how to play a text-based computer game with no prior assumptions about how language works. Although the system can’t complete the game as a whole, its ability to complete sections of it suggests that, in some sense, it discovers the meanings of words during its training.
In 2011, professor of computer science and engineering Regina Barzilay and her students reported a system that learned to play a computer game called “Civilization” by analyzing the game manual. But in the new work, on which Barzilay is again a co-author, the machine-learning system has no direct access to the underlying “state” of the game program — the data the program is tracking and how it’s being modified.
“When you play these games, every interaction is through text,” says Karthik Narasimhan, an MIT graduate student in computer science and engineering and one of the new paper’s two first authors. “For instance, you get the state of the game through text, and whatever you enter is also a command. It’s not like a console with buttons. So you really need to understand the text to play these games, and you also have more variability in the types of actions you can take.”
Narasimhan is joined on the paper by Barzilay, who’s his thesis advisor, and by fellow first author Tejas Kulkarni, a graduate student in the group of Josh Tenenbaum, a professor in the Department of Brain and Cognitive Sciences. They presented the paper last week at the Empirical Methods in Natural Language Processing conference.
Gordian “not”
The researchers were particularly concerned with designing a system that could make inferences about syntax, which has been a perennial problem in the field of natural-language processing. Take negation, for example: In a text-based fantasy game, there’s a world of difference between being told “you’re hurt” and “you’re not hurt.” But a system that just relied on collections of keywords as a guide to action would miss that distinction.
So the researchers designed their own text-based computer game that, though very simple, tended to describe states of affairs using troublesome syntactical constructions such as negation and conjunction. They also tested their system against a demonstration game built by the developers of Evennia, a game-creation toolkit. “A human could probably complete it in about 15 minutes,” Kulkarni says.
To evaluate their system, the researchers compared its performance to that of two others, which use variants of a technique standard in the field of natural-language processing. The basic technique is called the “bag of words,” in which a machine-learning algorithm bases its outputs on the co-occurrence of words. The variation, called the “bag of bigrams,” which looks for the co-occurrence of two-word units.
On the Evennia game, the MIT researchers’ system outperformed systems based on both bags of words and bags of bigrams. But on the homebrewed game, with its syntactical ambiguities, the difference in performance was even more dramatic. “What we created is adversarial, to actually test language understanding,” Narasimhan says.
Deep learning
The MIT researchers used an approach to machine learning called deep learning, a revival of the concept of neural networks, which was a staple of early artificial-intelligence research. Typically, a machine-learning system will begin with some assumptions about the data it’s examining, to prevent wasted time on fruitless hypotheses. A natural-language-processing system could, for example, assume that some of the words it encounters will be negation words — though it has no idea which words those are.
Neural networks make no such assumptions. Instead, they derive a sense of direction from their organization into layers. Data are fed into an array of processing nodes in the bottom layer of the network, each of which modifies the data in a different way before passing it to the next layer, which modifies it before passing it to the next layer, and so on. The output of the final layer is measured against some performance criterion, and then the process repeats, to see whether different modifications improve performance.
In their experiments, the researchers used two performance criteria. One was completion of a task — in the Evennia game, crossing a bridge without falling off, for instance. The other was maximization of a score that factored in several player attributes tracked by the game, such as “health points” and “magic points.”
On both measures, the deep-learning system outperformed bags of words and bags of bigrams. Successfully completing the Evennia game, however, requires the player to remember a verbal description of an engraving encountered in one room and then, after navigating several intervening challenges, match it up with a different description of the same engraving in a different room. “We don’t know how to do that at all,” Kulkarni says.
“I think this paper is quite nice and that the general area of mapping natural language to actions is an interesting and important area,” says Percy Liang, an assistant professor of computer science and statistics at Stanford University who was not involved in the work. “It would be interesting to see how far you can scale up these approaches to more complex domains.”
-
Resume Full name Sayed Ahmadreza Razian Age 38 (Sep 1982) Website ahmadrezarazian.ir Email ahmadrezarazian@gmail.com Education MS...
-
Shangul Mangul HabeAngur Shangul Mangul HabeAngur (City of Goats) is a game for child (4-8 years). they learn how be useful in the city and respect to people. Persian n...
-
Drowning Detection by Image Processing In this research, I design an algorithm for image processing of a swimmer in a pool. This algorithm diagnostics the swimmer status. Every time graph s...
-
Tianchi-The Purchase and Redemption Forecasts 2015 Special Prize – Tianchi Golden Competition (2015) “The Purchase and Redemption Forecasts” in Big data (Alibaba Group) Among 4868 teams. Introd...
-
معرفی نام و نام خانوادگی سید احمدرضا رضیان پست الکترونیکی ahmadrezarazian@gmail.com درجات علمی کارشناسی : ریاضی کاربردی – دانشگاه اصفهان (معدل 14...
-
Nokte – نکته نرم افزار کاربردی نکته نسخه 1.0.8 (رایگان) نرم افزار نکته جهت یادداشت برداری سریع در میزکار ویندوز با قابلیت ذخیره سازی خودکار با پنل ساده و کم ح...
-
Tianchi-Brick and Mortar Store Recommendation with Budget Constraints Ranked 5th – Tianchi Competition (2016) “Brick and Mortar Store Recommendation with Budget Constraints” (IJCAI Socinf 2016-New York,USA)(Alibaba Group...
-
1st National Conference on Computer Games-Challenges and Opportunities 2016 According to the public relations and information center of the presidency vice presidency for science and technology affairs, the University of Isfah...
-
Optimizing raytracing algorithm using CUDA Abstract Now, there are many codes to generate images using raytracing algorithm, which can run on CPU or GPU in single or multi-thread methods. In t...
-
2nd Symposium on psychological disorders in children and adolescents 2016 2nd Symposium on psychological disorders in children and adolescents 2016 Faculty of Nursing and Midwifery – University of Isfahan – 2 Aug 2016 - Ass...
-
My City This game is a city simulation in 3d view. Gamer must progress the city and create building for people. This game is simular the Simcity.
-
ببین و بپر به زودی.... لینک صفحه : http://bebinbepar.ir
-
Environmental Education Software In this game , Kids learn that They must respect to Nature and the Environment. This game was created in 3d . 600x420 (0x0) 66.45 KB ...
-
SVM Review On this review, i compare 4 papers about 4 famous models by SVM. These models are : Maximum Likelihood Classification (ML) Backpropagatio...
-
Watching Jumping Coming Soon... Visit at : http://bebinbepar.ir/
- AMD Ryzen Downcore Control AMD Ryzen 7 processors comes with a nice feature: the downcore control. This feature allows to enable / disabl...
- Fallout 4 Patch 1.3 Adds NVIDIA HBAO+ and FleX-Powered Weapon Debris Fallout 4 launched last November to record player numbers, swiftly becoming the most popular third-party game...
- Detecting and Labeling Diseases in Chest X-Rays with Deep Learning Researchers from the National Institutes of Health in Bethesda, Maryland are using NVIDIA GPUs and deep learni...
- NVIDIA TITAN Xp vs TITAN X NVIDIA has more or less silently launched a new high end graphics card around 10 days ago. Here are some pictu...
- Automatic Colorization Automatic Colorization of Grayscale Images Researchers from the Toyota Technological Institute at Chicago and University of Chicago developed a fully aut...
- Back to Dinosaur Island Back to Dinosaur Island takes advantage of 15 years of CRYENGINE development to show users the sheer endless p...
- Unity – What’s new in Unity 5.3.3 The Unity 5.3.3 public release brings you a few improvements and a large number of fixes. Read the release not...
- ASUS GeForce GTX 1080 TURBO Review This GTX 1080 TURBO is the simplest GTX 1080 I tested. By simplest, I mean the graphics card comes with a simp...
- Assisting Farmers with Artificial Intelligence With our planet getting warmer and warmer, and carbon dioxide levels steadily creeping up, companies are using...
- کودا – CUDA کودا به انگلیسی (CUDA) که مخفف عبارت انگلیسی Compute Unified Device Architecture است یک سکوی پردازش موازی و مد...
- Virtual Reality in the Military Virtual reality has been adopted by the military – this includes all three services (army, navy and air force)...
- Diablo Meets Dark Souls in Isometric Action-RPG Eitr Among the indie games Sony showcased during its E3 press conference this week, Eitr was what most stood out to...
- Diagnosing Cancer with Deep Learning and GPUs Using GPU-accelerated deep learning, researchers at The Chinese University of Hong Kong pushed the boundaries...
- Head-mounted Displays (HMD) Head-mounted displays or HMDs are probably the most instantly recognizable objects associated with virtual rea...
- How to Enable GodMode in Windows 10The GodMode of Windows 10 is nothing else than a …
- Historical Mortal Kombat 1 in 3DMortal Kombat is an arcade fighting game developed and published …
- Assessing Traumatic Brain Injuries with Deep LearningMore than one million athletes experience a concussion each year …
- New App Automatically Identifies Your Best PhotosFinding all the best pictures on your phone just became …
- Deep Learning for Computer Vision with MATLAB and cuDNNDeep learning is becoming ubiquitous. With recent advancements in deep …
- Fable Legends: AMD and Nvidia go head-to-head in latest DirectX 12 benchmarkAs DirectX 12 and Windows 10 roll out across the …
- Microsoft confirms there will be no Windows 11Microsoft says that Windows 10 will be its final release …
- Red’s Dream-PIXAR 1987-John LasseterRed's Dream is a 1987 American computer-animated short film produced …
- Global Impact: How GPUs Help Eye Surgeons See 20/20 in the Operating RoomEditor’s note: This is one in a series of profiles …
- Upcoming Webinar: Machine Learning and Computer Vision are Redefining Visual SearchEvery second, Millions of videos are generated and consumed every …
Leave a Reply