| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Learning Top-Down Tree Transducers with Regular Domain Inspection
Abstract : We study the problem of how to learn tree transformations on a given regular tree domain from a finite sample of input-output examples. We assume that the target tree transformation can be defined by a deterministic top-down tree transducer with regular domain inspection (DTOPi:reg). An RPNI style learning algorithm that solves this problem in polynomial time and with polynomially many examples was presented at Pods'2010, but restricted to the case of path-closed regular domains. In this paper, we show that this restriction can be removed. For this, we present a new normal form for DTOPi:reg by extending the Myhill-Nerode theorem for DTOP to regular domain inspections in a nontrivial manner. The RPNI style learning algorithm can also be lifted but becomes more involved too.
Cited literature [13 references]
https://hal.inria.fr/hal-01357186
Contributor : Inria Links <>
Submitted on : Monday, August 29, 2016 - 2:00:38 PM
Last modification on : Friday, December 11, 2020 - 6:44:06 PM
Long-term archiving on: : Wednesday, November 30, 2016 - 1:58:13 PM
Contributor : Inria Links <>
Submitted on : Monday, August 29, 2016 - 2:00:38 PM
Last modification on : Friday, December 11, 2020 - 6:44:06 PM
Long-term archiving on: : Wednesday, November 30, 2016 - 1:58:13 PM
File
0.pdf
Files produced by the author(s)