Facebook researchers use maths for better translations

Facebook, Google and Microsoft as well as Russia’s Yandex, China’s Baidu and others are constantly seeking to improve their translation tools. (File/AFP)
Updated 13 October 2019
Follow

Facebook researchers use maths for better translations

  • Facebook researchers say rendering words into figures and exploiting mathematical similarities between languages is a promising avenue
  • Allowing as many people as possible worldwide to communicate is not just an altruistic goal, but also good business

PARIS: Designers of machine translation tools still mostly rely on dictionaries to make a foreign language understandable. But now there is a new way: numbers.

Facebook researchers say 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 and others are constantly seeking to improve their translation tools.

Facebook has artificial intelligence experts on the job at one of its research labs in Paris. Up to 200 languages are currently used on Facebook, said Antoine Bordes, European co-director of fundamental AI research for the social network.

Automatic translation is currently based on having large databases of identical texts in both languages to work from. But for many language pairs there just aren’t enough such parallel texts.

That’s 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 current machine translation system is “equal or maybe a bit worse” than the word vector system, said Lample.

But for the rarer language pair of English-Urdu, where Facebook’s traditional system doesn’t have many bilingual texts to reference, the word vector system is already superior, he said.

But could the method allow translation from, say, Basque into the language of an Amazonian tribe? In theory, yes, said Lample, but in practice a large body of written texts are 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 CNRS national scientific center said the approach Lample has taken for Facebook could produce useful results, even if it doesn’t result in perfect translations.

Thierry Poibeau of CNRS’s Lattice laboratory, which also does research into 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, said Poibeau. 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’s 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, said Yvon, and could prove sufficient to track hate speech, a major priority for Facebook.


Dark times under Syria’s Assad hit Arab screens for Ramadan

Updated 6 sec ago
Follow

Dark times under Syria’s Assad hit Arab screens for Ramadan

  • Talking about Syria’s prisons and the torture, enforced disappearances and executions that took place there was taboo during half a century of the Assad family’s iron-fisted rule

 

BEIRUT: A Syrian prison warden screams at a group of chained, crouching inmates in a harrowing scene from one of several Ramadan television series this year that tackle the era of former ruler Bashar Assad.
Talking about Syria’s prisons and the torture, enforced disappearances and executions that took place there was taboo during half a century of the Assad family’s iron-fisted rule, but the topics are now fertile ground for creative productions, though not without controversy.
An abandoned soap factory north of the Lebanese capital Beirut has been transformed into a replica of the basements and corridors of Syria’s Saydnaya prison, a facility synonymous with horror under Assad, for the series “Going Out to the Well.”
Crews were filming the last episodes this week as the Muslim holy month kicked off — primetime viewing in the Arab world, with channels and outlets furiously competing for eager audiences’ attention.
Director Mohammed Lutfi told AFP that “for Syrians, Saydnaya prison is a dark place, full of stories and tales.”
The series focuses on the 2008 prison riots in Saydnaya, “when inmates revolted against the soldiers and took control of the prison, and there were negotiations between them and Syrian intelligence services,” he said.
The military prison, one of Syria’s largest and which also held political prisoners, remains an open wound for thousands of families still looking for traces of their loved ones.

Tragedy into drama

The Association of Detainees and Missing Persons of Saydnaya Prison estimates that some 30,000 people were thrown into the facility after the 2011 uprising against Assad began, but only 6,000 came out after he was toppled.
Amnesty International has described the prison outside Damascus, which was notorious for torture and enforced disappearances, as a “human slaughterhouse.”
In the opening scene of the series, the main character is seen in a tense exchange with his family before jumping into a deep well.

A local guides journalists visiting the Palmyra Prison Complex formerly used by the ousted Assad government in Syria's central city of Palmyra on February 7, 2025. (AFP)

The symbolic scene in part captures the struggles of the detainees’ relatives. Many spent years going from one Assad-era security facility to another in search of their missing family members.
Syrian writer Samer Radwan said on Facebook that he finished writing the series several months before Assad’s fall.
Director Lutfi had previously told AFP that challenges including actors’ fears of the Assad authorities’ reaction had prevented filming until after his ouster.
Since then, productions have jumped on the chance to finally tackle issues related to his family’s brutal rule.
Another series titled “Caesar, no time, no place” presents testimonies and experiences based on true stories from inside Syria’s prisons during the civil war, which erupted in 2011.
But in a statement this week, the Caesar Families Association strongly rejected “transforming our tragedy into dramatic material to be shown on screen.”
“Justice is sought in court, not in film studios,” said the association, whose name refers to thousands of images smuggled out of Syria more than a decade ago showing bodies of people tortured and starved to death in the country’s prisons.

Refugees
Another series, “Governorate 15,” sees two Saydnaya inmates, one Lebanese and one Syrian, leave the facility after Assad’s fall and return to their families.
Producer Marwan Haddad said that the series tackles the period of “the Syrian presence in Lebanon” through the Lebanese character.
The show also addresses the Syria refugee crisis through the story of the Syrian character’s family, who fled to the struggling neighboring country to escape the civil war.
“For years we said we didn’t want Lebanon to be (Syria’s) 15th province” and each person fought it in their own way, said Lebanese screenwriter Carine Rizkallah.
Under Assad’s father Hafez, Syria’s army entered Lebanon in 1976 during the country’s civil war and only left in 2005 after dominating all aspects of Lebanese life for almost three decades.
It was also accused of numerous political assassinations.
Lebanese director Samir Habchy said that the actors represent their “own community’s problems” in the “Lebanese-Syrian series.”
The show could prove controversial because it includes real people who “are still alive and will see themselves” in the episodes, he added.