seq2seq_chatbot_links下载 - seq2seq_chatbot

seq2seq_chatbot_links

Ai源码

1.0.0

下载

seq2seq 聊天机器人链接

不同框架的神经会话模型实现的链接。欢迎贡献。

西亚诺，烤宽面条

Lukalabs/cakechat

能够在文本对话中表达情感的对话系统。请参阅在线演示。

中性情绪的示例结果：

 hi                                → hey you
how are you ?                     → i ' m fine , what about you ?
how old are you ?                 → i ' m 16 , how old are you ?
are you a leader or a follower ?  → i ' m a man who is a politician .
my name is david . what is my name ?    → i love your name .
is the sky blue or black ?        → the sky is blue
you love anime .                  → i ' m not a weeb

张量流

Conchylicultor/DeepQA

不错的结果：

 Hi			            	→ Hi.
What is your name ?			→ Laura.
What does that mean ?		→ I dunno.
How old are you ?			→ thirty-five.
Who is Laura ?				→ My brother.
Say 'goodbye'				→ Alright.
Two plus two				→ manny...

尼古拉斯-伊万诺夫/tf_seq2seq_chatbot

修改机器翻译模型的代码。此代码中没有实现回答随机化，因此模型每次都以相同的短语方式回答：

 hello baby					→ hello
how old are you ?			→ twenty .
i am lonely					→ i am not
nice						→ you ' re not going to be okay .
so rude						→ i ' m sorry .
are you a robot or human?	→ no .
are you better than siri?	→ yes .

火炬

jiweil/神经对话生成

Jiwei Li 撰写的一系列超级好文章的源代码 - 这是我在神经会话系统领域最喜欢的研究之一。值得一看。

 tell me ... how long have you had this falling sickness ?   → a few months, I guess .
so i had the doctors test sammy ’s response to conditioning .   → so he took the pills .
what are you going to do ?  → i ’m going to get you a new car .
they fear your power your intellect .   → i ’m not afraid of your power .

马库诺耶/neuralconvo

 Hello?					→ Hi.
How are you?			→ I'm fine.
What's your name?		→ It's hard to describe.
How so?					→ I'm not sure.
What color is the sky?	→ It's blue.
What is your job?		→ It's not that i'm a fucking werewolf!

喀拉斯

法里兹拉赫曼4u/seq2seq

GitHub 上最流行的 Seq2seq 架构实现。然而，仍然没有证据表明此存储库取得了良好的结果。

尼古拉斯-伊万诺夫/debug_seq2seq

用于运行实验的 farizrahman4u/seq2seq 的包装器。到目前为止还没有取得好的结果。

Codekansas/keras 语言建模

需要检查一下。

oswaldoludwig/Seq2seq-Chatbot-for-Keras

一种新的生成聊天机器人，其训练在几个时期内收敛，包括在从在线英语课程对话中收集的小型但一致的数据集上进行预训练的模型。

 user: Hello! How are you?
computer:  i am fine , ok , well , thank you  .    (with probability of 0.540239)
user: What's your name?
computer:  janet .     (with probability of 0.319482)
user:  What do you like to do now?
computer:  let me think a minute .     (with probability of 0.286760)
user: I want to chat about computer science.
computer:  i am glad to hear there .     (with probability of 0.293063)
user: Are you a real girl or a computer program?
computer:  i am self employed . i would love to be well .     (with probability of 0.026870)
user: Why don't you look for a job?
computer:  i do not know . i am the bank .     (with probability of 0.053494)
user: So, you don't need a job!
computer:  no . i have to make a lot of money .     (with probability of 0.001279)