Accéder au contenu principal

How Google Converted Language Translation Into a Problem of Vector Space Mathematics

Technology Review (09/25/13) 

Google researchers have developed a technique that uses vector space mathematics for language conversion. Instead of using versions of the same document in different languages, the technique relies on data mining to model the structure of a single language and then compares this to another language's structure. Their method is based on the notion that all languages have to describe a similar set of ideas, requiring similar words to accomplish this. The researchers determined a way to represent a language using the relationship between its words. The set of all the relationships, or the language space, can be visualized as a set of vectors pointing from one word to another; linguists recently have found that these vectors can be approached mathematically. Converting one language into another becomes a mathematical task of determining the transformation that converts one vector space into the other. To map the vector spaces, the researchers use a small bilingual dictionary developed by humans that compares the same body of words in two languages, to lay the groundwork for the linear transformation. The mapping can then be applied to larger language spaces. The researchers note that although their method is simple, it achieves almost 90-percent precision for English and Spanish translation, and is equally effective with less closely-related languages, such as English and Vietnamese.

Posts les plus consultés de ce blog

Expérience professionnelle Cnam Liban informatique

Au Cnam Liban 1/3 des crédits environs sont attribués à l'expérience professionnelle, voici les conditions de validation de cette expérience:

Source : département informatique Cnam Liban , Computer Science Lebanon for adult training and continuous training
Les titres du répertoire national des certifications professionnelles (RNCP)Les diplômes de niveau III (bac+2) :
2 ans d’expérience professionnelle dans le domaine ou 2 ans en dehors du domaine
+ 3 mois de stage dans la spécialitéLes diplômes de niveau II (bac+3/4) :
2 ans d’expérience professionnelle dans le domaine ou 3 ans en dehors du domaine
+ un stage de 3 à 6 mois selon la spécialitéLes licencesParcours complet L1, L2, L3
3 ans d’expérience professionnelle dont 1 an dans le domaine validé par un rapport
d’activité. Si l’expérience professionnelle est en dehors de la spécialité : 3 ans + 6 mois de
stage dans la spécialitéParcours L3
1 an d’expérience professionnelle dans le domaine validé par un rapport d’activité.
Si l’expérience…

LTE IoT: Sequans Claims 'Big Lead' over Rivals

Sequans : With the promise of growth in the cellular IoT market, Sequans (Paris, France) is coming to Las Vegas this week to unveil what the company calls “the world’s first purpose-built Cat M1/NB1 chip” at CTIA’s Super Mobility Week.

Specifically designed for narrowband IoT applications by Release 13 of the 3GPP LTE standard, Cat M1 and Cat NB1 are expected to bring better coverage and a longer battery life to wearable devices, industrial monitors and low-data, sensor-driven IoT networks.

Category M1, also known as LTE-M and Cat M, delivers about 1 Megabit per second (Mbps) maximum in a 1.4 MHz channel. Category NB1, also previously known as NB-IoT, delivers about 40 kilobit per second (kbps) in a 200 kHz channel.
Full article :