seq2seq_chatbot_links Unduh - seq2seq_chatbot

seq2seq_chatbot_links

Kode Sumber AI

1.0.0

Unduh

tautan chatbot seq2seq

Tautan ke implementasi model percakapan saraf untuk kerangka kerja yang berbeda. Kontribusi disambut baik.

Theano, Lasagna

lukalabs/cakechat

Sebuah sistem dialog yang mampu mengekspresikan emosi dalam percakapan teks. Lihat demo online.

Contoh hasil untuk emosi netral:

 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

Aliran Tensor

Conchylicultor/DeepQA

Hasil yang bagus:

 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...

nicolas-ivanov/tf_seq2seq_chatbot

Kode model terjemahan mesin yang dimodifikasi. Tidak ada pengacakan jawaban yang diterapkan dalam kode ini, sehingga model menjawab dengan cara frasa yang sama setiap kali:

 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 .

Obor

jiweil/Generasi Dialog Neural

Kode sumber untuk sekumpulan artikel super bagus oleh Jiwei Li - salah satu penelitian favorit saya di bidang sistem percakapan saraf. Layak untuk dicoba.

 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 .

macournoyer/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!

keras

farizrahman4u/seq2seq

Implementasi arsitektur Seq2seq paling populer di GitHub. Namun, masih belum ada bukti mendapatkan hasil yang baik dengan repo ini.

nicolas-ivanov/debug_seq2seq

Pembungkus untuk farizrahman4u/seq2seq yang digunakan untuk menjalankan eksperimen. Sejauh ini belum ada hasil baik yang dicapai.

codekansas/keras-bahasa-modeling

Perlu memeriksa ini.

oswaldoludwig/Seq2seq-Chatbot-for-Keras

Chatbot generatif baru yang pelatihannya menyatu dalam beberapa periode, termasuk model yang telah dilatih sebelumnya pada kumpulan data kecil namun konsisten yang dikumpulkan dari dialog kursus bahasa Inggris online.

 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)