AI还能写好笑话吗？

刚刚观看了有关虚拟助手讲笑话的最新WIRED视频。它们是由人类组成的，但是我想知道AI是否已经足够好来编写一些。

我认为AI尚未达到这一点。以下是一些有关该主题的有趣论文：

• 最近写了一篇论文，试图利用无监督学习来开玩笑。这些笑话是公式化的：它们都是“我喜欢我的X就像我喜欢我的Y：Z”的形式，其中X和Y是名词，而Z是可以形容X和Y的形容词。本文产生的笑话：

  I like my relationships like I like my source, open
  I like my coffee like I like my war, cold
  I like my boys like I like my sectors, bad
  

  我猜这些笑话有多有趣是个人喜好问题。

• 达里奥·贝特罗（Dario Bertero）和帕斯卡尔·冯（Pascale Fung）的另一篇论文利用LSTM从大爆炸理论显示的数据集中预测幽默。这不是在生成笑话，而是找出笑话在此数据集中的位置（因此，从理论上讲，所得的标记数据集有望用于训练模型以创建笑话）。

• 还有另一篇论文是何仁，全阳。与上面提到的无监督的第一篇论文不同，这是一种有监督的学习模型。他们的神经网络模型产生了如下笑话：

  Apple is teaming up with Playboy Magazine in the self driving office.
  One of the top economy in China , Lady Gaga says today that Obama is legal.
  Google Plus has introduced the remains that lowers the age of coffee.
  According to a new study , the governor of film welcome the leading actor of Los Angeles area , Donald Trump .
  

我的两分钱：

在撰写本文时，看来用于字符级语言模型的多层递归神经网络（LSTM，GRU，RNN）是迄今为止最有希望的解决方案。也许，如果您发现一些非常酷的数据，您可能会提出一些有趣的笑话，类似于Janelle Shane如何生成我发现非常有趣的拾取行，例如：

Are you a 4loce? Because you’re so hot!
I want to get my heart with you.
You are so beautiful that you know what I mean.
I have a cenver? Because I just stowe must your worms.
Hey baby, I’m swirked to gave ever to say it for drive. 
If I were to ask you out?
You must be a tringle? Cause you’re the only thing here.
I’m not on your wears, but I want to see your start.
You are so beautiful that you make me feel better to see you.
Hey baby, you’re to be a key? Because I can bear your toot?
I don’t know you.
I have to give you a book, because you’re the only thing in your eyes.
Are you a candle? Because you’re so hot of the looks with you.
I want to see you to my heart.
If I had a rose for every time I thought of you, I have a price tighting.
I have a really falling for you.
Your beauty have a fine to me.
Are you a camera? Because I want to see the most beautiful than you.
I had a come to got your heart.
You’re so beautiful that you say a bat on me and baby.
You look like a thing and I love you.
Hello.

截至目前，我们还没有令人满意的幽默认知理论（或者至少可以评估笑话的幽默性），因此对文献的快速调查似乎表明我们对幽默没有太多了解如何建立模型。

因此，现有的方法似乎不能可靠地产生良好的笑话形式，因此似乎没有理由相信ML方法可以产生良好的笑话。

但这当然是规范性的。