 |
Laboratoire d'informatique fondamentale de Marseille UMR 6166 - CNRS, Université de la Méditerranée, Université de Provence |
 |
|
Laboratoire d'informatique fondamentale de Marseille UMR 6166 - CNRS, Université de la Méditerranée, Université de Provence |
|
| HAL: hal-00293511, version 3 |
| Detailed view |  Export this paper |
 |
| International Colloquium on Grammatical Inference, St Malo : France (2008) |
|
|
| Available versions: | v3 (2008-09-10) |
|
|
|
|
| Relevant Representations for the Inference of Rational Stochastic Tree Languages |
|
|
| François Denis 1Edouard Gilbert 2, 3 |
|
|
| (2008) |
|
|
|
| Recently, an algorithm, DEES, was proposed for learning rational stochastic tree languages. Given an independantly and identically distributed sample of trees, drawn according to a rational stochastic language, DEES outputs a linear representation of a rational series which converges to the target. DEES can then be used to identify in the limit with probability one rational stochastic tree languages. However, when DEES deals with finite samples, it often outputs a rational tree series which does not define a stochastic language. Moreover, the linear representation can not be directly used as a generative model. In this paper, we show that any representation of a rational stochastic tree language can be transformed in a reduced normalised representation that can be used to generate trees from the underlying distribution. We also study some properties of consistency for rational stochastic tree languages and discuss their implication for the inference. We finally consider the applicability of DEES to trees built over an unranked alphabet. |
|
|
|
|
|
|
|
|
|
|
|
| 1: | Laboratoire d'informatique Fondamentale de Marseille (LIF) |
|
|
|
CNRS : UMR6166 – Université de la Méditerranée - Aix-Marseille II – Université de Provence - Aix-Marseille I |
|
|
| 2: | Laboratoire d'Informatique Fondamentale de Lille (LIFL) |
|
|
|
CNRS : UMR8022 – Université Lille I - Sciences et technologies – Université Lille III - Sciences humaines et sociales – INRIA |
|
|
| 3: | MOSTRARE (INRIA Lille - Nord Europe) |
|
|
|
INRIA – CNRS : UMR8022 – Université Lille I - Sciences et technologies – Université Lille III - Sciences humaines et sociales |
|
|
|
|
|
|
|
|
|
| Subject | : | Computer Science/Learning |
|
|
| Attached file list to this document: | |||||
|
|||||
|
|
|
| hal-00293511, version 3 | |
| http://hal.archives-ouvertes.fr/hal-00293511 | |
| oai:hal.archives-ouvertes.fr:hal-00293511 | |
| From: Marc Tommasi | |
| Submitted on: Wednesday, 10 September 2008 13:47:49 | |
| Updated on: Tuesday, 18 November 2008 20:34:44 | |
