英语翻译这个晚上大家辛苦了.还是麻烦简练翻译.In Google’s vision of the future,peop

英语翻译
这个晚上大家辛苦了.还是麻烦简练翻译.
In Google’s vision of the future,people will be able to translate documents instantly into the world’s main languages,with machine logic,not expert linguists,leading the way.
Google’s approach,called statistical(统计的) machine translation,differs from past efforts in which it does without language experts who program grammatical rules and dictionaries into computers.Instead,they feed documents humans have already translated into two languages and then rely on computers to decide patterns for future translations.
While the quality is not perfect,it is an improvement on previous efforts at machine translation,said Franz Och,35,a German who heads Google’s translation effort at its Mountain View headquarters south of San Francisco.“Some people who have been in machine translations for a long time see our Arabic-English output,and then they say,that’s amazing,that’s a breakthrough.” Said Och.“And then other people who have never seen what machine translation was read through the sentence and they say,the first mistake here in Line Five－it doesn’t seem to work because there is a mistake there.”
But for some tasks,a mostly correct translation may be good enough.Speaking over lunch this week in a Google cafeteria famed for offering free,healthy food,Och showed a translation of an Arabic Web news site into easily digestible English.
Two Google workers speaking Russian at a nearby table said,however,that a translation of a news site from English into their native tongue was understandable but a bit awkward.Och,who speaks German,English and some Italian,feeds hundreds of millions of words from parallel texts such as Arabic and English into the computer,using United Nations and European Union documents as key sources.
Languages without considerable translated texts,such as some African languages,face greater obstacles.“The more data we feed into the system,the better it gets.” said Och,who moved to the United States from Germany in 2002.
The program applies statistical analysis,an approach he hopes will avoid diplomatic embarrassing mistakes in diplomatic situations,such as when Russian leader Putin’s translator annoyed then German Chancellor(总理) Gerhard Schroeder by calling him the German “Fuhrer (“leader” in English),” which is forbidden in that context because of its association with Adolf Hitler.
“I would hope that the language model would say,well,Schroeder is…very rare but Bundeskanzler Gerhard Schroeder is probably 100 times more frequent than Fuhrer and then it would make the right decision.” Och said.

在Google的展望未来,人们将能够翻译文件即刻融入世界的主要语言,随着机器的逻辑,而不是专家,语言学家,一路领先.
Google的做法,所谓的统计（统计的）机器翻译,不同于以往的努力,其中不无语言专家,他们计划语法规则及字典到他们的电脑里.相反,它们的饲料证件人类已经翻译成两种语言,然后再依赖电脑来决定的模式,为今后的翻译本.
而素质不完美,但它是一种进步对先前的努力机器翻译说,德国och , 35 ,一个德国人元首Google的翻译工作,在其芒廷维尤总部以南的旧金山. "有些人已经在机器翻译在相当长的时间,看看我们的阿拉伯语-英语输出,然后他们说,这是了不起的, that'sa突破.说： " och . "然后其他的人,从来没有见过什么机器翻译是通读一句,他们说,第一个错误,在此线的五年,它似乎没有工作,因为有一个错误,有" .
但在执行一些任务时,大多是正确的翻译可能会不够好.谈到在午餐这个星期在Google的咖啡闻名,提供免费的健康食品, och显示翻译的一个阿拉伯文网站新闻网站成易于消化的英语.
Google的两名工人讲俄语附近的一个表说,不过,这一个翻译的新闻网站从英文翻译成他们的母语是可以理解的,但有点尴尬. och ,谁讲德语,英语和一些意大利,饲料,数以亿计的话,从平行文本,如用阿拉伯文和英文输入电脑,利用联合国和欧洲联盟的文件,作为主要来源.
语文没有相当翻译文本,例如一些非洲语言,面临着更大的障碍. "更详尽资料,我们饲料的进排水系统,更好地得到它说： " och ,他移居美国,从德国在2002年.
该计划适用于统计分析中,一种方法,他希望能够避免外交尴尬的失误,在外交情况,例如当俄罗斯领导人普京的翻译懊恼当时的西德（总理）德国总理施罗德致电他的德国" fuhrer （ "领袖"在英语） , "这是被禁止的,在此背景下,因为它会与希特勒.
"我希望,这个语言模型会说,好,施罗德是…非常罕见,但bundeskanzler总理施罗德可能是100倍,更频密的,比fuhrer然后它会做出正确的决定" . och说.
有些单词你好象打错了,不过我也给你翻译的差不多了.