Machine Learning Models of Universal Grammar Parameter Dependencies

Dimitar Kazakov, Guido Cordoni, Andrea Ceolin, Monica-Alexandrina Irimia, Shin-Sook Kim, Dimitris Michelioudakis, Nina Radkevich, Cristina Guardiano, Giuseppe Longobardi

[How to correct problems with metadata yourself]

Abstract
The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky’s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study.
Anthology ID:
W17-7805
Volume:
Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017
Month:
September
Year:
2017
Address:
Varna
Editors:
Kalliopi Zervanou, Petya Osenova, Eveline Wandl-Vogt, Dan Cristea
Venue:
RANLP
SIG:
Publisher:
INCOMA Inc.
Note:
Pages:
31–37
Language:
URL:
https://doi.org/10.26615/978-954-452-040-3_005
DOI:
10.26615/978-954-452-040-3_005
Bibkey:
Cite (ACL):
Dimitar Kazakov, Guido Cordoni, Andrea Ceolin, Monica-Alexandrina Irimia, Shin-Sook Kim, Dimitris Michelioudakis, Nina Radkevich, Cristina Guardiano, and Giuseppe Longobardi. 2017. Machine Learning Models of Universal Grammar Parameter Dependencies. In Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017, pages 31–37, Varna. INCOMA Inc..
Cite (Informal):
Machine Learning Models of Universal Grammar Parameter Dependencies (Kazakov et al., RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-040-3_005
PDF Search