Deep Tree Transductions - A Short Survey

Abstract

The paper surveys recent extensions of the Long-Short Term Memory networks to handle tree structures from the perspective of learning non-trivial forms of isomorph structured transductions. It provides a discussion of modern TreeLSTM models, showing the effect of the bias induced by the direction of tree processing. An empirical analysis is performed on real-world benchmarks, highlighting how there is no single model adequate to effectively approach all transduction problems.

To appear in the Proceedings of the 2019 INNS Big Data and Deep Learning (INNSBDDL 2019). arXiv admin note: text overlap with arXiv:1809.09096