MDDs: Sampling and Probability Constraints
We propose to combine two successful techniques of Artificial Intelligence: sampling and Multi-valued Decision Diagrams (MDDs). Sampling, and notably Markov sampling, is often used to generate data resembling to a corpus. However, this generation has usually to respect some additional constraints, for instance to avoid plagiarism or to respect some rules of the application domain. We propose to represent the corpus dependencies and these side constraints by an MDD and to develop some algorithms for sampling the solutions of an MDD while respecting some probabilities or a Markov chain. In that way, we obtain a generic method which avoids the development of ad-hoc algorithms for each application as it is currently the case. In addition, we introduce new constraints for controlling the probabilities of the solutions that are sampled. We experiments our method on a real life application: the geomodeling of a petroleum reservoir, and on the generation of French alexandrines. The obtained results show the advantage and the efficiency of our approach.
This research is conducted within the Flow Machines project which received funding from the European Research Council under the European Unions Seventh Framework Programme (FP/2007–2013)/ERC Grant Agreement no. 291156. We would like to thank F. Pachet and P. Roy, who gave us the idea of this article.
- 2.Barbieri, G., Pachet, F., Roy, P., Esposti, M.D.: Markov constraints for generating lyrics with style. In: ECAI 2012–20th European Conference on Artificial Intelligence, pp. 115–120 (2012)Google Scholar
- 7.Brooks, F., Hopkings, A., Neumann, P., Wright, W.: An experiment in musical composition. 3(6), 175–182 (1957)Google Scholar
- 9.Hadzic, T., Hooker, J.N., ÓSullivan, B., Tiedemann, P.: Approximate compilation of constraints into multivalued decision diagrams. In: Stuckey, P.J. (ed.) CP 2008. LNCS, vol. 5202, pp. 448–462. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-85958-1_30
- 11.Jurafsky, D., Martin, J.H.: Speech and Language Processing. Pearson, London (2014)Google Scholar
- 13.Nierhaus, G.: Algorithmic Composition: Paradigms of Automated Music Generation. Springer, Heidelberg (2009)Google Scholar
- 15.Pachet, F., Roy, P., Barbieri, G.: Finite-length Markov processes with constraints. IJCAI 2011, 635–642 (2011)Google Scholar
- 16.Papadopoulos, A., Roy, P., Pachet, F.: Avoiding plagiarism in Markov sequence generation. In: Proceeding of the Twenty-Eight AAAI Conference on Artificial Intelligence, pp. 2731–2737 (2014)Google Scholar
- 18.Papadopoulos, A., Roy, P., Régin, J.-C., Pachet, F.: Generating all possible palindromes from Ngram corpora. In: Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2015, 25–31 July 2015, Buenos Aires, Argentina, pp. 2489–2495 (2015)Google Scholar
- 19.Pennington, W.D.: Reservoir geophysics 66(1) (2001)Google Scholar
- 21.Perez, G., Régin, J.-C.: Efficient operations on MDDs for building constraint programming models. In: International Joint Conference on Artificial Intelligence, IJCAI 2015, Argentina, pp. 374–380 (2015)Google Scholar
- 22.Perez, G., Régin, J.-C.: Soft and cost MDD propagators. In: The Thirty-First AAAI Conference on Artificial Intelligence AAAI 2017 (2017)Google Scholar
- 24.Roy, P., Pachet, F.: Enforcing meter in finite-length Markov sequences. In: AAAI 2013 (2013)Google Scholar