AGL 40.26 Increased By ▲ 0.26 (0.65%)
AIRLINK 127.05 Increased By ▲ 0.01 (0.01%)
BOP 6.62 Decreased By ▼ -0.05 (-0.75%)
CNERGY 4.49 Decreased By ▼ -0.02 (-0.44%)
DCL 8.63 Increased By ▲ 0.08 (0.94%)
DFML 41.85 Increased By ▲ 0.41 (0.99%)
DGKC 87.60 Increased By ▲ 0.75 (0.86%)
FCCL 32.85 Increased By ▲ 0.57 (1.77%)
FFBL 65.25 Increased By ▲ 0.45 (0.69%)
FFL 10.28 Increased By ▲ 0.03 (0.29%)
HUBC 109.90 Increased By ▲ 0.33 (0.3%)
HUMNL 14.85 Increased By ▲ 0.17 (1.16%)
KEL 5.12 Increased By ▲ 0.07 (1.39%)
KOSM 7.53 Increased By ▲ 0.07 (0.94%)
MLCF 41.70 Increased By ▲ 0.32 (0.77%)
NBP 59.51 Decreased By ▼ -0.90 (-1.49%)
OGDC 194.29 Increased By ▲ 4.19 (2.2%)
PAEL 28.29 Increased By ▲ 0.46 (1.65%)
PIBTL 7.82 Decreased By ▼ -0.01 (-0.13%)
PPL 152.30 Increased By ▲ 2.24 (1.49%)
PRL 26.55 Decreased By ▼ -0.33 (-1.23%)
PTC 16.12 Increased By ▲ 0.05 (0.31%)
SEARL 83.00 Decreased By ▼ -3.00 (-3.49%)
TELE 7.65 Decreased By ▼ -0.06 (-0.78%)
TOMCL 35.45 Increased By ▲ 0.04 (0.11%)
TPLP 8.19 Increased By ▲ 0.07 (0.86%)
TREET 16.19 Decreased By ▼ -0.22 (-1.34%)
TRG 52.90 Decreased By ▼ -0.39 (-0.73%)
UNITY 26.50 Increased By ▲ 0.34 (1.3%)
WTL 1.25 Decreased By ▼ -0.01 (-0.79%)
BR100 9,952 Increased By 68 (0.69%)
BR30 30,896 Increased By 296.2 (0.97%)
KSE100 93,919 Increased By 563.7 (0.6%)
KSE30 29,100 Increased By 168.8 (0.58%)

Google is promising that its widely used translation service is now even more fluent, thanks to an advance that's enabling its computers to interpret complete sentences. That may sound simple, but it took years of engineering to pull off. Until now, Google's technology analysed phrases in pieces and then cobbled together a sometimes stilted translation.
Now that Google's machines can interpret entire sentences, the translations of extended passages of text should read and sound much more like a native speaker of the language. The technology, dubbed "neural machine translation," is similar to what Google has been using for the past few years to identify people and objects in pictures stored in its Photos service.
Google described its neural machine tool as the biggest leap for its translation service in a decade.
Forrester Research analyst Mike Gualtieri also believes Google's new method is a significant breakthrough, although he said he expects it to make some potentially embarrassing mistakes in its early stages, much like the Photos service misidentified some things when it first rolled out.
"I doubt it will be translating like the computers on 'Star Trek' quite yet," Gualtieri said.
Starting Tuesday, the technology is being be used to translate phrases to and from English and eight other languages ? French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish.
Those languages cover about one-third of all the translation requests that Google gets. It says that on average it translates about 140 billion words per day for the more than 500 million people who use the service.
Google, part of Alphabet Inc, eventually hopes to apply the neural machine technology on all 103 languages in its translation service.

Copyright United Press of Pakistan, 2015

Comments

Comments are closed.