Text Generation from Keywords

I would like to generate Text based on Keywords. This means, not specific seed text for a Language Model to complete. Rather a neural network, which given some keywords, would generate a text of x words long, including as most of these keywords as possible.

For example, for a domain specific network in Fashion, with the Keywords light, dress, orange, cotton. It could output: This gorgeous orange summer dress is great for wearing on sunny camping days. It's cotton fabric makes it very comfortable to wear.

I’ve seen people are trying GANs to do this. I was wondering if any has experience with this, implemented this, or would recommend to try it in a different way (other than GANs)?

Any advice or hint is mostly welcome!

1 Like

I’m very interested to discuss your progress on this topic, or exchange ideas

Sure @jeremyeast. I have not started yet with this project, but I’ll be sure to discuss some early results as I get there.

I am trying to work on the same project as yours. Can anyone provide some insights on how to approach this problem? Generating text using specific keywords!

Dear friends,

I 'm looking idea for this kind of project as well, could you please suggest some?

1 Like

Just to bring the topic up again. any news on this topic?

Hi ! New projects come up back then and I didn’t have the time to pursuit this further. I know of a few companies doing this though, including axsemantics and textengine. But I haven’t seen any open source implementation. I’ll have more time in November and I’d like to collaborate if someone is interested as well :slight_smile:


@cduguet, yes. If I would love to talk more about the problem.

1 Like

@cduguet I want to work on a business case according this problem would like to join!

1 Like

Keen to hear more about this as hoping to do the same! Any updates?