Designers of machine translation tools still mostly rely on dictionaries to make a foreign language understandable. However, now there is a new way: numbers.
Facebook researchers said rendering words into figures and exploiting mathematical similarities between languages is a promising avenue — even if a universal communicator a la Star Trek remains a distant dream.
Powerful automatic translation is a big priority for Internet giants. Allowing as many people as possible worldwide to communicate is not just an altruistic goal, but also good business.
Facebook, Google and Microsoft as well as Russia’s Yandex, China’s Baidu (百度) and others are constantly seeking to improve their translation tools.
Facebook has artificial intelligence (AI) experts on the job at one of its research labs in Paris.
Up to 200 languages are used on Facebook, said Antoine Bordes, European codirector of fundamental AI research for the social network.
Automatic translation is based on having large databases of identical texts in both languages to work from.
However, for many language pairs there just are not enough such parallel texts.
That is why researchers have been looking for another method, like the system developed by Facebook, which creates a mathematical representation for words.
Each word becomes a “vector” in a space of several hundred dimensions. Words that have close associations in the spoken language also find themselves close to each other in this vector space.
“For example, if you take the words ‘cat’ and ‘dog,’ semantically, they are words that describe a similar thing, so they will be extremely close together physically” in the vector space, said Guillaume Lample, one of the system’s designers. “If you take words like Madrid, London, Paris, which are European capital cities, it’s the same idea.”
These language maps can then be linked to one another using algorithms — at first roughly, but eventually becoming more refined, until entire phrases can be matched without too many errors.
Lample said results are already promising.
For the language pair of English-Romanian, Facebook’s machine translation system is “equal or maybe a bit worse” than the word vector system, Lample said.
However, for the rarer language pair of English-Urdu, where Facebook’s traditional system does not have many bilingual texts to reference, the word vector system is already superior, he said.
However, could the method allow translation from, say, Basque into the language of an Amazonian tribe?
In theory, yes, Lample said, but in practice a large body of written texts is needed to map the language, something lacking in Amazonian tribal languages.
“If you have just tens of thousands of phrases, it won’t work. You need several hundreds of thousands,” he said.
Experts at France’s national scientific center, CNRS, said the approach Lample has taken for Facebook could produce useful results, even if it does not result in perfect translations.
Thierry Poibeau of CNRS’ Lattice laboratory, which also researches machine translation, called the word vector approach “a conceptual revolution.”
He said “translating without parallel data” — dictionaries or versions of the same documents in both languages — “is something of the Holy Grail” of machine translation.
“But the question is what level of performance can be expected” from the word vector method, Poibeau said.
The method “can give an idea of the original text,” but the capability for a good translation every time remains unproven.
Francois Yvon, a researcher at CNRS’ Computer Science Laboratory for Mechanics and Engineering Sciences, said “the linking of languages is much more difficult” when they are far removed from one another.
“The manner of denoting concepts in Chinese is completely different from French,” he added.
However, even imperfect translations can be useful and could prove sufficient to track hate speech, a major priority for Facebook, Yvon said.
Eleven people, including a former minister, were arrested in Serbia on Friday over a train station disaster in which 16 people died. The concrete canopy of the newly renovated station in the northern city of Novi Sad collapsed on Nov. 1, 2024 in a disaster widely blamed on corruption and poor oversight. It sparked a wave of student-led protests and led to the resignation of then-Serbian prime minister Milos Vucevic and the fall of his government. The public prosecutor’s office in Novi Sad opened an investigation into the accident and deaths. In February, the public prosecutor’s office for organized crime opened another probe into
RISING RACISM: A Japanese group called on China to assure safety in the country, while the Chinese embassy in Tokyo urged action against a ‘surge in xenophobia’ A Japanese woman living in China was attacked and injured by a man in a subway station in Suzhou, China, Japanese media said, hours after two Chinese men were seriously injured in violence in Tokyo. The attacks on Thursday raised concern about xenophobic sentiment in China and Japan that have been blamed for assaults in both countries. It was the third attack involving Japanese living in China since last year. In the two previous cases in China, Chinese authorities have insisted they were isolated incidents. Japanese broadcaster NHK did not identify the woman injured in Suzhou by name, but, citing the Japanese
YELLOW SHIRTS: Many protesters were associated with pro-royalist groups that had previously supported the ouster of Paetongtarn’s father, Thaksin, in 2006 Protesters rallied on Saturday in the Thai capital to demand the resignation of court-suspended Thai Prime Minister Paetongtarn Shinawatra and in support of the armed forces following a violent border dispute with Cambodia that killed more than three dozen people and displaced more than 260,000. Gathered at Bangkok’s Victory Monument despite soaring temperatures, many sang patriotic songs and listened to speeches denouncing Paetongtarn and her father, former Thai prime minister Thaksin Shinawatra, and voiced their backing of the country’s army, which has always retained substantial power in the Southeast Asian country. Police said there were about 2,000 protesters by mid-afternoon, although
MOGAMI-CLASS FRIGATES: The deal is a ‘big step toward elevating national security cooperation with Australia, which is our special strategic partner,’ a Japanese official said Australia is to upgrade its navy with 11 Mogami-class frigates built by Japan’s Mitsubishi Heavy Industries, Australian Minister for Defence Richard Marles said yesterday. Billed as Japan’s biggest defense export deal since World War II, Australia is to pay US$6 billion over the next 10 years to acquire the fleet of stealth frigates. Australia is in the midst of a major military restructure, bolstering its navy with long-range firepower in an effort to deter China. It is striving to expand its fleet of major warships from 11 to 26 over the next decade. “This is clearly the biggest defense-industry agreement that has ever
RSS