So like they generated many, many sentences and asked people to rate which ones are good and which ones are not good.

就像他们生成了很多很多的句子，然后让人们评价哪些是好的，哪些是不好的。

They basically fine tune the model so that it would generate sentences that are convincing to people.

他们基本上是对模型进行微调，使其能够生成令人信服的句子。

To illustrate, if you type in the word " splitting" into COCA, and then it will automatically generate, say, a thousand sentences for you.

例如，当你在 COCA 输入 splitting，它会自动产生大概一千个句子。

So to teach a computer to see a picture and generate sentences, the marriage between big data and machine learning algorithm has to take another step.

因此，要教导计算机看到图并说出句子，必须进一步地仰赖庞大资料群以及机器的学习演算。

And then they feed it a bunch of text so it can learn the patterns of which words generally follow which other words, and eventually it learns to generate its own sentences.

然后他们给它提供了一堆文本，这样它就可以学习模式即哪些词一般跟在哪些词后面，最终它学会了生成自己的句子。