Improving the Markov Chain Approach for Generating Text Used for Ideation Tasks

Isaac Terngu Adom¹

1. Department of Mathematics and Computer Science, Benue State University, Makurdi, Nigeria.

Section:Research Paper, Product Type: Journal-Paper
Vol.11 , Issue.4 , pp.45-50, Aug-2023

Online published on Aug 31, 2023

Copyright © Isaac Terngu Adom . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

109 Views    128 Downloads    26 Downloads

Abstract :
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 Artificial intelligence. Creative text ideas have been sought after for innovation, problem solving, and improvements, and coming up with them can be a daunting task. In this work, an idea generation system based on improvements to the Markov chain 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 solution text from 200 participants was clustered based on similarity measures into groups, and abstractive summaries of the respective groups were computed. The Markov chain model was then used for the generation of new text from the submitted text corpus, and the most similar Markov chain-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 Pretrained Transformer system using the same text corpus, and this work’s system performed better.

Key-Words / Index Term :
Computational Creativity, Ideation, Markov Chain, Text Generation, Artificial Intelligence, Innovation, Crowd Sourcing

References :
[1] C. Riedl, N. May, J. Finzenc, S. Stathel, V. Kaufman, and H. Krcmar. “An Idea Ontology for Innovation Management.” International Journal on Semantic Web and Information Systems (IJSWIS) vol. 5, no. 4, pp. 1–18. 2014. doi: 10.4018/jswis.2009100101.
[2] M. A. Boden. The Creative Minds: Myths and Mechanisms (2nd Edition). New York, USA: Routledge, 2004. isbn: 0203508521.
[3] S. Colton and G. A. Wiggins. “Computational Creativity: The final frontier?” Proceedings of 20th European Conference on Artificial Intelligence (ECAI). pp. 21–26, 2012.
[4] A. Graves. “Generating Sequences With Recurrent Neural Networks.” Neural and Evolutionary Computing, Computer Science, Cornell University. pp. 1–10, 2014.
[5] D. Pawade and A. Sakhapara. “Story Scrambler - Automatic Text Generation Using Word Level RNN-LSTM.” International Journal of Information Technology and Computer Science pp. 44–53, 2018. doi: 10.5815/ ijitcs.2018.06.05.
[6] D. Eck and J. Schmidhuber. A First Look At Music Composition Using LSTM Recurrent Neural Networks. Technical Report. Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale.
[7] Y. Zhu, S. Lu, L. Zheng, J. Guo, W. Zhang, J. Wang, and Y. Yu. “Texygen: A Benchmarking Platform for Text Generation Models.” Proceedings of The 41st International ACM SIGIR Conference. 2018.
[8] S. D. Raut and S. A. Thorat. “Deep Learning Techniques: A Review” International Journal of Scientific Research in Computer Science and Engineering vol. 8, no. 1, pp.105-109, 2020.
[9] M.M. Mastoli, U.R. Pol, and R. Patil. “AI for Diabetic Retinopathy” International Journal of Scientific Research in Computer Science and Engineering vol 7, no. 6, pp.30-35, 2012.
[10] J. Finzen, M. Kintz, and S. Kaufman. “Aggregating Web-Based Platforms.” International Journal of Technology Intelligence and Planning vol. 8, no. 1, pp. 32–46, 2012. doi: 10.1504/IJTIP.2012.047376.
[11] K. Girotra, C. Terwiesch, and K. Ulrich. “Generation and the Quality of the Best Idea.” Management Science vol. 56, no. 4, pp. 591–605, 2010. doi: 10.5815/ijitcs.2018.06.05.
[12] B. Pratyush, D. Kui, C. Abhijit, and A. M. Narendra. “Idea Co-creation on Social Media Platforms: towards a theory of social ideation” Journal of Information Systems and Analytics. 2020
[13] J. Chan, S. Dang, and S.P. Dow. “Comparing Different Sensemaking Approaches for Large-Scale Ideation” Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems pp. 2717 – 2728, 2016. doi: https://doi.org/10.1145/2858036.2858178
[14] M. Pedro, M. Jose, and A. Fernando. “An Approach of an Idea Management Platform to Improve the Innovation Process” International Journal of Computer Applications Vol. 103, pp. 41 – 47, 2014. doi: 10.5120/18130-9231
[15] P. Siangliulue, K. C. Arnold, K. Z. Gajos, S. P. Dow. “Towards Collaborative Ideation at Scale: Leveraging Ideas from Others to Generate More Creative and Diverse Ideas” Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing pp. 937 – 945, 2015. doi: https://doi.org/10.1145/2675133.2675239
[16] M. Hossain, and K.M.Z. Islam “Ideation Through Online Open Innovation Platform: Dell IdeaStorm” International Journal of Knowledge Economy vol. 6, pp. 611 – 624. doi: 10.1007/s13132-015-0262-7
[17] D. Bettiga and L. Lamberti. "Crowd Size and Crowdsourcing Performances in Online Ideation Contests," 16th International Conference on Service Systems and Service Management (ICSSSM), pp. 1-6, 2019. doi: 10.1109/ICSSSM.2019.8887700.
[18] Ö. Altay and B. Christine. “Idea Evaluation in Innovation Contest Platforms: A Network Perspective”. Journal of Decision Support Systems vol. 112, 2018. doi: 10.1016/j.dss.2018.06.001
[19] A. Mohammadi, E. Javanmardi, and H. Dastyar. “Applying a Markov Chain Model for Screening of New Product Ideas” Journal of Applied Mathematics in Engineering, Management and Technology vol. 3, no. 4, pp. 126 – 135, 2015
[20] Y. Zhongliang, J. Shuyu, H. Yongfeng, Z. Yujin and L. Hui. “Automatically Generate Stenographic Text Based on Markov Model and Huffman Coding” Cryptography and Security: IETE Technical Review. 2018 doi: https://doi.org/10.48550/arXiv.1811.04720
[21] H. C. F. Carlos. “Creating Recipes using Machine Learning and Computational Creativity.” MSc. Thesis, Dept. Of Info. Systems & Comp. Engr., Tech. Uni. Lisbon, Lisbon, 2018.
[22] L. Haixia. “Automatic Idea Generation and Analysis Using NLP and ML Techniques.” PhD thesis. Sch. Of Comp. Sc., Uni. Of Nottingham, Malaysia, 2019.
[23] D. Cer, Y. Yang, S. Kong, N. Hua, N. Limtiacob, R. John, N. Constant, M. Guajardo-Cespedes, et al. Universal Sentence Encoder. Technical report. Google, 2019.
[24] J.N. Madhuri and G. Kumar. “Extractive Text Summarization Using Sentence Ranking.” Proceedings of International Conference on Data Science and Communication. pp. 1–3, 2019.
[25] H. Lin and V. Ng. “Abstractive Summarization: A Survey of the State of the Art.” Proceedings of AAAI Conference on Artificial Intelligence. pp. 9815–9822, 2019.
[26] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, and Y. Zhou. “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.” Journal of Machine Learning Research. pp. 1–67, 2020.
[27] C. Grinstead and L. Snell. Introduction to Probability (2nd Edition). USA: American Mathematical Society, isbn: 978-0821807491.
[28] J. Agbinya. Markov Chain and its Applications an Introduction, 2020. ISBN: 978-87-7022-096-5 978-87-7022-095-8
[29] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever. Language Models are Unsupervised Multitask Learners, OpenAI, San Francisco, California, United States 2018.
[30] J. Han, F. Shi, L. Chen, and P. Childs. “The Combinator – a computer- based tool for creative idea generation based on a simulation approach.” Design Science 4, 2018.