Learning Sequential Tree-to-Word Transducers

Grégoire Laurence 1, 2 Aurélien Lemay 1, 2 Joachim Niehren 1, 2 Slawomir Staworko 1, 2 Marc Tommasi 1, 3
2 LINKS - Linking Dynamic Data
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
3 MAGNET - Machine Learning in Information Networks
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
Abstract : 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 (STW). 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.

A long version is available here

Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00912969
Contributor : Joachim Niehren <>
Submitted on : Tuesday, December 3, 2013 - 8:53:37 AM
Last modification on : Thursday, February 21, 2019 - 10:52:55 AM
Long-term archiving on : Monday, March 3, 2014 - 10:15:47 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00912969, version 1

Citation

Grégoire Laurence, Aurélien Lemay, Joachim Niehren, Slawomir Staworko, Marc Tommasi. Learning Sequential Tree-to-Word Transducers. 8th International Conference on Language and Automata Theory and Applications, Mar 2014, Madrid, Spain. ⟨hal-00912969⟩

Share

Metrics

Record views

697

Files downloads

299