We study the problem of learning sequential top-down tree-to-word transducers (stws). First, we present a Myhill-Nerode characterization of the corresponding class of sequential tree-to-word transformations ( TeX ). Next, we investigate what learning of stws means, identify fundamental obstacles, and propose a learning model with abstain. Finally, we present a polynomial learning algorithm.
|Title of host publication||Language and Automata Theory and Applications|
|Subtitle of host publication||8th International Conference, LATA 2014, Madrid, Spain, March 10-14, 2014. Proceedings|
|Publisher||Springer International Publishing|
|Number of pages||13|
|Publication status||Published - 2014|