Did you know Bot Libre also provides free hosted live chat for your own website or mobile app?
Bot Libre Forum

How to generate haiku poetry using deep learning

by admin posted Mar 7 2022, 13:23

The Bot Libre platform is not just a bot platform, but also a platform for artificial intelligence and deep learning. With Bot Libre you can create your own deep learning neural network for text classification, text generation, image recognition, audio and speech recognition, object detection, games, prediction, data analysis, and more.

You may think that creating a "deep learning neural networks" sounds like a very complex thing to do, but with Bot Libre it is very simple, and requires no programming or data science experience. This article we walk you through the steps to create your own text generation network.

Step 1 - Find Sample Text

First you need to decide what types of text you want your network to generate. You can train a network to generate any type of text in any language, as long as you have some sample text files. The more sample text the better. You can upload a single text file, or multiple files.

For this article, we will train a network to generate a poetry haiku fragment. The goal is to be able to give it a topic, or the first haiku line, and it will generate the poem or second and third lines.

First you need to find some sample text files. You can create your own text data, or download an existing dataset. Here is an existing set of English haiku poems, https://www.kaggle.com/hjhalani30/haiku-dataset

Step 2 - Create Analytic

Next we need to create our analytic on Bot Libre.

  • Click browse analytics on Bot Libre
  • Click on New Analytic
  • Enter a name and category and click "Create"

Step 3 - Configure Analytic

Next we need to configure the analytic.

  • Click on the analytic's "Admin Console" button or menu.
  • Click on "Analytic Network"
  • Under "Analytic Type" select "RNN Text Generation"
  • It will auto-fill the other settings, click the Save button

The other analytic type settings let you create different types of networks.

Step 4 - Upload Text Files

Next we need to upload our text files.

  • Click on the "DataRepository" button, menu, or link in the analytic's Admin Console
  • Click on add label (green plus), enter "haiku"
  • Select the "haiku" label and click the upload button, select your haiku text file

Step 5 - Train Network

Next we need to train the network.

  • Click on the "Train Network" button, menu, or link in the analytic's Admin Console
  • Click on "Train", this may take a while

Step 6 - Test Network

Now you can test your network.

  • Click on the "Test Network" button from the analytic's main page
  • Upload a text file to test, or enter some text
  • It will return you a paragraph of generated text based on the text fragment or topic

If you get poor results, or text that does not make sense you most likely need to train your network longer.

Your Done

You can now access your analytic from Bot Libre's website and share it with your friends. You can also access your analytic through the Bot Libre web API from your own website or app. You can download your network as a ".zip" file for usage with Tensorflow.

Here is the fully trained analytic, Haiku Generator

Bot Libre will be adding support for training more network types in the coming months. You can also train your network manually using python and Tensorflow, this is very complicated and requires some development and python experience. We can also develop a deep learning neural network for you through the Bot Libre AI development services, contact [email protected].


Id: 42180667
Tags: nlp, analytics, deep learning, text generation
Posted: Mar 7 2022, 13:23
Updated: Mar 7 2022, 13:31
Replies: 0
Views: 2330, today: 2, week: 2, month: 19
0 1 5.0/5