Learning Sequential Tree-to-Word Transducers

Grégoire Laurence, Aurélien Lemay, Joachim Niehren, Slawek Staworko, Marc Tommasi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationLanguage and Automata Theory and Applications
Subtitle of host publication8th International Conference, LATA 2014, Madrid, Spain, March 10-14, 2014. Proceedings
PublisherSpringer International Publishing
Number of pages13
ISBN (Electronic)978-3-319-04921-2
ISBN (Print)978-3-319-04920-5
Publication statusPublished - 2014


Dive into the research topics of 'Learning Sequential Tree-to-Word Transducers'. Together they form a unique fingerprint.

Cite this