阅读流畅的机器翻译是怎样一种体验

北极光创投 2016-10-25 10:46 工具软件 来源:创头条 查看原文
一篇英文的长篇专业文章摆在面前,想了解里面说了啥你的通常做法是什么?谷歌,还是百度?翻译出来的文字可能依然会面临“相见不相识”的尴尬,依然需要耗费时力才能清楚了解文章的意思。

    得益于人工智能、深度神经网络学习、大数据等的快速发展,机器翻译已能模仿人脑“理解语言,生成译文”。准确度、流畅度都得到大幅提高,甚至达到“译文流畅,符合语法规范,易于理解”的状态。

    北极光投资的Atman(爱特曼)作为国内少有关注机器翻译并追求自动化的创业公司,就一直致力于此并在机器翻译的专业指标上已经遥遥领先。说的好不如做的到,本着求真精神,适逢我们投资的另外一家AI领域的公司(Drive.AI)的创始人近日在MIT Technology Review上发表了一篇有关自动驾驶深度学习的文章“Deep Driving”, 我们通过Atman在短短数秒内将文章翻译如下,全文未经人工修饰,机器“裸翻”,分享给各位,欢迎欣赏、评论、吐槽。我们也相信:阅读,在未来,可以变的更享受。

Deep Driving
 
A revolutionary AI technique is about to transform the self-driving car.
一种革命性的人工智能技术将要改变自动驾驶车。
October 18, 2016
2016 年 10 月 18 日
 

When the Google self-driving-car project began about a decade ago, the company made a strategic decision to build its technology on expensive lidar and detailed mapping. Even today, Google’s self-­driving technology still relies on those two pillars. While that approach is great up to a point—we have good algorithms for using lidar and camera data to localize a car on the map—it’s still not good enough. Driving on complicated, ever-changing streets involves perception and decision-making skills that are inherently uncertain (see “Your Driverless Ride Is Arriving”).

在 10 年前谷歌开始自动驾驶汽车项目时 ,该公司做出了一项战略决定 ,将在昂贵的激光雷达和详细绘图方面建立起它的技术。即便是今天,谷歌的自动驾驶技术仍依赖于这两个支柱 。虽然这种方法很好,但我们有好的算法来使用激光雷达和照相机数据将汽车定位在地图上。 但它仍然不够好。在复杂 、 不断变化的街道上驾驶,涉及到一种内在不确定的观念和决策技能 。
 

Now an artificial-intelligence technology called deep learning is being used to address the problem. Rather than using the old method of hand-coded algorithms, we can now use systems that program themselves by learning from examples of how a system ought to behave in response to an input. Deep learning is now the best approach to most perception tasks, as well as to many low-level control tasks.

现在,正在利用一种称为深度学习的人工智能技术来解决这个问题。我们现在可以使用程序本身,而不是使用旧的手工编码算法,从一些例子中学习一个系统应该如何对输入作出反应。现在,深度学习是感知任务的最佳做法,也是许多低层级控制任务的最佳途径。
 

A self-driving car needs a perception system to sense things that are moving (cars, people) as well as things that aren’t (lampposts, curbs). Self-driving vehicles detect dynamic objects using sensors such as cameras, laser scanners, and radar. Of these three, cameras are the cheapest, but they’re also used the least because it’s hard to translate images into detected objects. Using deep learning, we’re seeing dramatic improvements in the car’s ability to understand and make use of such images.

一个自动驾驶的汽车需要一种感知系统,让人们感觉到正在移动的物体以及那些没有改变的物体。自动驾驶车辆使用照相机、激光扫描仪和雷达等传感器来检测动态物体。在这三种中,摄像机是最便宜的,但也被最少使用,因为很难将图像转换为检测对象。利用深度学习,我们看到汽车理解和使用这种图像的能力有了显著改善。
 

We’re also seeing significant gains from something called “multitask deep learning,” in which a system trained simultaneously to detect lane markings, cars, and pedestrians does better than three separate systems trained in isolation—since the single network can share information among the separate tasks.

我们还看到了从所谓的多任务深度学习中获得的可观收益,在该学习中,一个同步训练的 系统检测车道标志、汽车和行人。由于单一网络可以在不同的任务中共享信息,所以会比单独训练的三个独立系统要好。
 

Nvidia-Drive-PX-2-shown-in-action1.jpg

Instead of relying entirely on a pre-computed map, the car can use the map as one of many data streams, combining it with sensor inputs to help it make decisions. (A neural network that knows from map data where crosswalks are, for example, can more accurately detect pedestrians trying to cross than one that relies solely on images.)

汽车可以用地图作为许多数据流的一个, 而不是完全依靠一个预先计算的地图,从而将该地图与传感器的输入结合起来,以帮助它做出决定。例如,从地图数据中知道人行道的一个神经网络能够更准确地检测到试图穿越的行人,而不是仅仅依靠图像。
 

Deep learning can also alleviate one of the biggest issues identified by many who have ridden in a self-driving car—a “jerky” feel to the driving style, which sometimes leads to motion sickness. But a car trained using examples of humans driving can offer a ride that feels more natural.

深入学习也能缓解那些在自动驾驶汽车上乘坐的许多人发现的最大问题之一 ——颠簸的驾驶感觉,有时会导致晕车。但是,受过人工驾驶数据训练的汽车会让人们感觉更自然。
 

It’s still early. But just as deep learning did with image search and voice recognition, it is likely to forever change the course of self-driving cars.

现在还为时过早。但是,正如深度学习在图像搜索和语音识别上所做的那样,它有可能永远改变自动驾驶汽车的过程。
 
Carol Reiley is the cofounder of Drive.ai.
Carol Reiley是Drive.ai创始人之一。


为您推荐: