The problem with meaning in the texts generated by the AI?

0 like 0 dislike
8 views
I decided to create an app that will write the tale based on an old Russian fairy tales. I decided to use Markov chains for this problem, but this resulted a new problem: the text after processing becomes meaningless. Searching the Internet for articles on account of writing artificial intelligence, I have not found any description of the logic of creating a logically complete story. Please help.
by | 8 views

3 Answers

0 like 0 dislike
Cm. here is the list.
You need to be able to do the same: Demo
5ae89a88b3320715879895.jpeg
by
0 like 0 dislike
the Markov chain always generate random data (garbage), just restricted to certain rules (dimensions of probability).
to raise the quality using competitive approaches GAN (to generate this approach is now at the forefront is).
read more here:
\rhttps://ru.wikipedia.org/wiki/%D0%93%D0%B5%D0%BD%D...
by
0 like 0 dislike
Well, as it AI we have is still there. There are some neural networks that work on specific tasks. But the main problem for you, the fact that neural networks do not understand the meaning of the text.
So, the task is currently not feasible. This requires "network", which grew up listening to tales from my mother in childhood, passed the stages of development of the personality, filled "bumps" so to speak.
Easier to hire a rewriter - man.
by

Related questions

0 like 0 dislike
2 answers
0 like 0 dislike
2 answers
0 like 0 dislike
1 answer
0 like 0 dislike
2 answers
110,608 questions
257,186 answers
0 comments
33,868 users