刚刚观看了最近关于虚拟助手在讲笑话方面表现的 WIRED 视频。它们是由人类组成的,但我想知道人工智能是否已经足够好,可以写一些了。
AI还能写出好笑话吗?
我认为人工智能还没有达到这一点。以下是一些关于该主题的有趣论文:
最近写了一篇论文,试图使用无监督学习来生成笑话。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,Z 是可以描述 X 和 Y 的形容词。这里有一些本文产生的笑话:
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
我猜这些笑话有多好笑是个人品味的问题。
Dario Bertero 和 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,而是找出在该数据集中讲笑话的位置(因此理论上,生成的标记数据集有望用于训练模型以创建笑话)。
还有一篇论文是何仁、全扬的。与上面提到的第一篇论文是无监督的不同,这是一个有监督的学习模型。他们的神经网络模型会生成以下笑话:
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,用于字符级语言模型的多层循环神经网络(LSTM、GRU、RNN)似乎是迄今为止最有希望的方法。也许如果您发现一些非常酷的数据,您可以想出一些有趣的笑话,类似于Janelle Shane能够生成我认为非常有趣的提词,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.
到目前为止,我们还没有一个令人满意的幽默认知理论(或者至少,一个可以评估笑话的欢闹性的理论),所以对文献的快速调查似乎表明我们对幽默没有太多的线索如何建立模型。
正因为如此,以及现有方法似乎不能可靠地产生自由形式的好笑话这一事实,似乎没有理由相信 ML 方法可以产生好笑话。
当然,这都是规范的。
令人惊讶的是,我刚刚发现了一个关于此的声明。我刚刚在 twitter 上看到它,该模型只是一个 GPT-2,具有 355M 参数,训练有 200,000 个原始标题和基于正文的笑话。令人惊奇的是,GPT-2 是最先进的文本生成模型,如果训练有素,它甚至可以翻译或回答数学问题。
让我们看看 twitter 的示例输出。
https://twitter.com/lgbtinethiopia/status/1294644776772472834?s=20