다양한 프레임워크에 대한 신경 대화 모델 구현에 대한 링크입니다. 기여를 환영합니다.
테아노, 라자냐
텍스트 대화에서 감정을 표현할 수 있는 대화 시스템입니다. 온라인 데모를 참조하세요.
중립 감정에 대한 샘플 결과:
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
텐서플로우
좋은 결과:
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...
기계 번역 모델의 수정된 코드입니다. 이 코드에서는 응답 무작위화가 구현되지 않으므로 모델은 매번 동일한 문구 방식으로 응답합니다.
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 .
토치
Jiwei Li가 작성한 매우 훌륭한 기사의 소스 코드 - 신경 대화 시스템 분야에서 제가 가장 좋아하는 연구 중 하나입니다. 확인해 볼 가치가 있습니다.
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 .
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!
케라스
GitHub에서 가장 널리 사용되는 Seq2seq 아키텍처 구현입니다. 그러나 이 저장소로 좋은 결과를 얻었다는 증거는 아직 없습니다.
실험을 실행하는 데 사용되는 Farizrahman4u/seq2seq의 래퍼입니다. 현재까지는 좋은 결과가 나오지 않았습니다.
이것을 확인해야합니다.
온라인 영어 코스의 대화에서 수집된 작지만 일관된 데이터 세트에 대해 사전 훈련된 모델을 포함하여 훈련이 몇 시대에 수렴되는 새로운 생성적 챗봇입니다.
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)
기존 대화 데이터 세트에 대한 훌륭한 개요입니다.
원본 영화 자막을 많이 받으세요(~1.2Gb)
기술 데이터를 지운 후 ~ 40Mb.
Richard Krisztian Csaky의 훌륭한 리뷰인 이미지가 포함된 챗봇 및 관련 연구 논문 노트를 참조하세요.
PDF로 된 보고서 논문: 딥 러닝 기반 챗봇 모델(Deep Learning Based Chatbot Models)