Scholars Central

Research articlePublished 31 May 2023

Markov Chains Text Generation for Ideation Platforms

Authors: Isaac Terngu Adom

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

Humankind has never experienced the geometric growth and interest in computing particularly in Artificial Intelligence (AI) like in recent times. Efficient processes, automated systems and improved decision making are some of the milestones of this trend. The increased demand for text related solutions from generation, learning, classification and several other tasks has motivated the use of different techniques and tools of AI. Creative text ideas have been sought after for innovation, problem solving and improvements. These ideas are needed in all endeavours of life as coming up with them can be a daunting task for individuals, organizations and ideation platforms. In this work, an idea generation system based on improvements of Markov chains approach using a corpus of text is presented. First, a web system was created to collect solutions from people on a case study problem. They were required to make submissions based on purpose and mechanism with examples to guide them. Next, the collected text was clustered based on similarity measure into groups, then abstractive summaries of the respective groups were computed. Markov chains model was then used to generate new text from the submitted text corpus and the most similar Markov chains generated text was compared with each clustered group’s abstractive summary using a similarity measure and returned as an idea result. Finally, a pipeline to execute all the components of the system at once was developed. The result was sent for human evaluation based on the metrics of quality, novelty and variety and compared with output from a generative transformer system using the same text corpus and this work’s system performed better. The work majorly addresses a challenge faced by ideation platforms.

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Similar by topic

More from this journal

The newest in Journal of Computer Engineering & Information Technology.

All its articles

Conferences in this field

Upcoming conferences in this field.

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • JournalJournal of Computer Engineering & Information Technology
  • SubjectComputer Science & IT
  • SubjectEngineering
  • BylineArticles whose byline prints “Isaac Terngu Adom”

For authors and organisers

Publish, present and keep up with your field

Find the right journal for your paper and submit your manuscript.

Photo: Pexels