homehome Home chatchat Notifications


AI learns to play chess by studying game commentaries instead of practicing

Instead of practicing millions of games, this machine analyzes the language of sports commentators to master chess.

Tibi Puiu
August 1, 2019 @ 8:03 pm

share Share

Credit: Pixabay.

Since Alan Turing wrote the first computer program for chess in 1951 (completely on paper) all the way to Gary Gasparov’s infamous loss at the proverbial hand of IBM’s Deep Blue supercomputer in 1998, chess has always been used as an indicator of progress for computers. Today, artificial intelligence systems are so advanced that humans barely have a chance at beating them. Google’s AlphaZero is a prime example; it started out knowing only the rules of chess and nothing more — no opening and closing moves, no libraries, nada. In a matter of hours, it had already played more games against itself than have ever been recorded in human chess history.

In a new study, researchers in artificial intelligence at University College London have yet again turned to chess. Only this time, their machine learning program didn’t practice millions of games to master chess but rather analyzed the language of expert commentators. Someday, the researchers say that a similar approach could allow machines to decipher emotional language and acquire skills which would have otherwise been inaccessible through ‘brute force’.

First, the researchers went through 2,700 chess game commentaries, which were pruned so that ambiguous or uninteresting moves were removed. They then employed a recurrent neural network —  a type of neural network where the output from the previous step is fed as input to the current step — and a mathematical technique called word embeddings to parse the language of the commentators.

The algorithm, called SentiMATE, worked out the basic rules of chess as well as several key strategies — including forking and castling — all by itself. On the flip side, it played quite poorly, at least, as compared to a grandmaster AI.

“We present SentiMATE, a novel end-to-end Deep Learning model for Chess, employing Natural Language Processing that aims to learn an effective evaluation function assessing move quality. This function is pre-trained on the sentiment of commentary associated with the training moves and is used to guide and optimize the agent’s game-playing decision making. The contributions of this research are three-fold: we build and put forward both a classifier which extracts commentary describing the quality of Chess moves in vast commentary datasets, and a Sentiment Analysis model trained on Chess commentary to accurately predict the quality of said moves, to then use those predictions to evaluate the optimal next move of a Chess agent,” the authors wrote.

High-level performance was not its objective, though. Where SentiMATE shines is in its ability to use language to acquire a skill instead of practicing it, thus employing less data and computing power than conventional approaches. AlphaZero, for instance, requires thousands of “little brain” — specialized chips called Tensor Processing Units (TPUs) — and millions of practice sessions to master games such as chess, Go, or Dota 2.

In a world with millions of books, blogs, and studies, machines like SentiMATE could find many practical applications. Such a machine, for instance, could learn to predict financial activities or write better stories simply by tapping into the sum of human knowledge.

SentiMATE was described in a paper published in the pre-print server ArXiv.

share Share

A Rocket Carried Cannabis Seeds and 166 Human Remains into Space But Their Capsule Never Made It Back

The spacecraft crashed into the Pacific Ocean after a parachute failure, ending a bold experiment in space biology and memorial spaceflight.

Ancient ‘Zombie’ Fungus Trapped in Amber Shows Mind Control Began in the Age of the Dinosaurs

The zombie fungus from the age of the dinosaurs.

Your browser lets websites track you even without cookies

Most users don't even know this type of surveillance exists.

What's Seasonal Body Image Dissatisfaction and How Not to Fall into Its Trap

This season doesn’t have to be about comparison or self-criticism.

Why a 20-Minute Nap Could Be Key to Unlocking 'Eureka!' Moments Like Salvador Dalí

A 20-minute nap can boost your chances of a creative breakthrough, according to new research.

The world's oldest boomerang is even older than we thought, but it's not Australian

The story of the boomerang goes back in time even more.

Swarms of tiny robots could go up your nose, melt the mucus and clean your sinuses

The "search-and-destroy” microrobot system can chemically shred the resident bacterial biofilm.

What if Every Roadkill Had a Memorial?

Road ecology, the scientific study of how road networks impact ecosystems, presents a perfect opportunity for community science projects.

Fireball Passes Over Southeastern United States

It’s a bird! It’s a plane! It’s… a bolide!

What side do cats prefer to sleep on? The left side, and there's a good reason for that

The fluffier side of science.