Inductive Inference of First-Order Models from Numeric-Symbolic Data

Floriana Esposito, Sergio Caggese, Donato Malerba, Giovanni Semeraro
Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics, PMLR R1:173-182, 1997.

Abstract

A factor common to statistical techniques of data analysis is the adopted representation formalism: A tabular (zeroth-order) model with almost exclusively numerical features . On the contrary, several studies on machine learning concern the induction of first-order models from symbolic data, but are inadequate for continuous data. In the paper, we face the problem of handling both numerical and symbolic data in first-order models. distinguishing the moment of model generation from examples (induction) from the moment of model recognition by means of a flexible. probabilistic subsumption test. We demonstrate the proposed solutions on a problem in document understanding where the objective is to induce the models of the logical structure of some real business letters.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR1-esposito97a, title = {Inductive Inference of First-Order Models from Numeric-Symbolic Data}, author = {Esposito, Floriana and Caggese, Sergio and Malerba, Donato and Semeraro, Giovanni}, booktitle = {Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics}, pages = {173--182}, year = {1997}, editor = {Madigan, David and Smyth, Padhraic}, volume = {R1}, series = {Proceedings of Machine Learning Research}, month = {04--07 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r1/esposito97a/esposito97a.pdf}, url = {https://proceedings.mlr.press/r1/esposito97a.html}, abstract = {A factor common to statistical techniques of data analysis is the adopted representation formalism: A tabular (zeroth-order) model with almost exclusively numerical features . On the contrary, several studies on machine learning concern the induction of first-order models from symbolic data, but are inadequate for continuous data. In the paper, we face the problem of handling both numerical and symbolic data in first-order models. distinguishing the moment of model generation from examples (induction) from the moment of model recognition by means of a flexible. probabilistic subsumption test. We demonstrate the proposed solutions on a problem in document understanding where the objective is to induce the models of the logical structure of some real business letters.}, note = {Reissued by PMLR on 30 March 2021.} }
Endnote
%0 Conference Paper %T Inductive Inference of First-Order Models from Numeric-Symbolic Data %A Floriana Esposito %A Sergio Caggese %A Donato Malerba %A Giovanni Semeraro %B Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 1997 %E David Madigan %E Padhraic Smyth %F pmlr-vR1-esposito97a %I PMLR %P 173--182 %U https://proceedings.mlr.press/r1/esposito97a.html %V R1 %X A factor common to statistical techniques of data analysis is the adopted representation formalism: A tabular (zeroth-order) model with almost exclusively numerical features . On the contrary, several studies on machine learning concern the induction of first-order models from symbolic data, but are inadequate for continuous data. In the paper, we face the problem of handling both numerical and symbolic data in first-order models. distinguishing the moment of model generation from examples (induction) from the moment of model recognition by means of a flexible. probabilistic subsumption test. We demonstrate the proposed solutions on a problem in document understanding where the objective is to induce the models of the logical structure of some real business letters. %Z Reissued by PMLR on 30 March 2021.
APA
Esposito, F., Caggese, S., Malerba, D. & Semeraro, G.. (1997). Inductive Inference of First-Order Models from Numeric-Symbolic Data. Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R1:173-182 Available from https://proceedings.mlr.press/r1/esposito97a.html. Reissued by PMLR on 30 March 2021.

Related Material