评论
打印
But again, it’s hard to know exactly what accuracy really means here.
但同样，很难确切知道这里的准确性意味着什么。
OK. Hold up, so the death calculator could also predict personality traits and if people would live abroad? Like how? I mean, how are those things related?
好，等等，死亡计算器也可以预测个性特征，以及人们是否会生活在国外？ 怎么可能？ 这些事情是如何关联的？
OK, Let’s take a step back here. Life2vec is a machine learning model, which basically just means it’s a big computer program made to detect patterns in very large sets of data.
让我们说回life2vec。life2vec是一个机器学习模型，基本上就是一个大型计算机程序，用于检测海量数据集的模型。
The researchers built this model and trained it on tons of government-collected information on millions of people living in Denmark.
研究人员建立了这个模型，并用政府收集的数百万丹麦人的信息对其进行训练。
They had employment history, basic demographic data, and also information on just about every interaction between people and the Danish medical system, because Denmark has universal healthcare.
这些信息包括就业历史、基本人口统计数据，以及人们与丹麦医疗系统之间的几乎所有互动的信息，因为丹麦实行全民医疗保健。
Wow, that must be nice.
哇，那一定很好。
Truly. Anyway, the researchers took all this data for each person and organized it into timelines.
确实如此。无论如何，研究人员将每个人的所有数据整理成时间线。
The life2vec model was fed all these timelines, and trained to pick up on patterns between the different events that show up in a person’s life.
在life2vec模型中输入所有这些时间线数据，并对其进行训练，以识别出一个人一生中发生的不同事件之间的模式。
You know, how are location and salary related? Do people diagnosed with certain diseases survive? Do people with certain professions tend to live longer?
位置和工资相关性如何？ 被诊断出患有某些疾病的人是否能存活下来吗？ 从事某些职业的人往往会更长寿吗？
Do people with certain career paths have certain personality traits?
从事某种职业的人是否具有某种性格特征？
Exactly. That's how you can go from something like demographic info to personality questionnaire.
确实如此。这就是从人口统计信息中预测个性问卷的方法。
That's so interesting.
这太有趣了。
From there, the researchers could ask versions of the model to make predictions based on those timelines.
基于此，研究人员可以要求不同版本的模型根据这些时间线做出预测。
The extra interesting thing with life2vec isn’t just that it makes these predictions–again we’ve been doing that forever–it’s how it does it.
life2vec的有趣之处不仅仅在于它可以进行这些预测(因为我们一直都在这样做)，更在于它是如何做到的。
It’s a type of mode usually used for chatbots and language processing. It basically runs like souped-up autocomplete.
这是一种通常用于聊天机器人和语言处理的模式。它的运行方式基本上就像增强型的“自动补全”功能一样。
Hah wait so the death predictions here are “autocompleting” someone’s life?
哈，等等，这里的死亡预测是“自动补全”某人的生命吗？
That is one way to put it. You give the model the life event timeline, you ask it a specific question, and it predicts the next relevant step in the timeline, based on the prompt. Sometimes that means predicting death.
这是一种输入方法。为模型输入生命事件的时间线，然后问它一个具体的问题，它会根据提示预测时间线上的下一个相关步骤。有时这意味着预测死亡。
Uh, kay yeah. This sounds like a Black Mirror episode.
嗯，好吧，这听起来像《黑镜》剧集里的情节。
Your phone’s autocomplete starts to spit out “you’ll die in seven days” type messages.
你的手机自动补全开始吐出的一条信息：“你将在七天内死亡”。
Pitch that to Netflix.
把这个推销给网飞。
I’m on it. We can be co-writers. So a little bit ago, you kept hedging on life2vec’s accuracy, what was that about?
我这就去写，我们可以成为合著者。刚才，你一直没有直接谈论life2vec的准确性，这到底是讲什么的？
Yeah, so I talked with some statistical and life modeling experts about this and none of them were super convinced by those 70+ percent accurate numbers that the researchers reported in the study.
是的，我与一些统计学家和生命建模专家谈论了这个工具的准确性，他们中没有人对研究报告中所说的70%以上的准确率有信心。
My favorite quote on these came from Christina Silcox, director for digital health at Duke Margolis Center for Health Policy.
关于这个观点，我最喜欢的的引述来自克里斯蒂娜·西尔科克斯，她是杜克马戈利斯卫生政策中心数字健康负责人。
