An Input-Output Bottom-up Hidden Tree Markov Model

The official Python implementation for the Bottom-up Hidden Tree Markov model (BHTMM) in its (more general) input-output version (IOBHTMM). The model learns a distribution over tree-structured data, implemented throughout a generative process acting from the leaves to the root of the tree.

The code is maintained in the Github of my student Federico Errica, who is to be credited for the implementation. To download the code and the scripts necessary to replicate the experiments in the original paper describing the model, please go here.

The code is provided as is with no warranty and technical support. Please inform the author (Davide Bacciu) if you intend to redistribute the code.

Citation

If you find this code useful, please remember to cite:

1. Bacciu Davide, Micheli Alessio, Sperduti Alessandro: Compositional Generative Mapping for Tree-Structured Data; Part I: Bottom-Up Probabilistic Modeling of Trees. In: Neural Networks and Learning Systems, IEEE Transactions on, vol. 23, no. 12, pp. 1987 -2002, 2012, ISSN: 2162-237X.
2. Bacciu Davide, Micheli Alessio, Sperduti Alessandro : An input–output hidden Markov model for tree transductions. In: Neurocomputing, vol. 112, pp. 34–46, 2013, ISSN: 0925-2312.