381 |
Análisis melódico de declarativas e interrogativas absolutas en español/LE
|
|
|
|
In: Phonica, Vol 5, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
382 |
Avaluació del desenvolupament fonològic en nens cataloparlants de 3, 4 i 5 anys
|
|
|
|
In: Phonica, Vol 1, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
383 |
Fonetometria: una proposta de protocol
|
|
|
|
In: Phonica, Vol 2, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
384 |
Identificació de les vocals tòniques del català
|
|
|
|
In: Phonica, Vol 3, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
385 |
Sobre el vocalismo y la pronunciación
|
|
|
|
In: Phonica, Vol 1, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
386 |
El mito del período crítico para el aprendizaje de la pronunciación de un idioma extranjero
|
|
|
|
In: Phonica, Vol 1, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
387 |
La enseñanza explícita de la pronunciación: creencias de los profesores y sus repercusiones en el aula de E/LE
|
|
|
|
In: Phonica, Vol 5, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
388 |
Análisis Melódico del Habla (AMH): 1999-2009
|
|
|
|
In: Phonica, Vol 5, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
389 |
Sobre la competència oral
|
|
|
|
In: Phonica, Vol 3, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
390 |
Protocolo para la extracción de datos tonales y curva estándar en análisis melódico del habla (AMH)
|
|
|
|
In: Phonica, Vol 6, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
391 |
Análisis multisistémico de las partículas modales del alemán. Volumen II - Anexos
|
|
|
|
In: Phonica, Vol 7, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
393 |
Melodic analysis of speech method (MAS) applied to Spanish and Catalan
|
|
|
|
In: Phonica, Vol 5, Iss 0 (2013) (2013)
|
|
BASE
|
|
Show details
|
|
394 |
Models for predicting the inflectional paradigm of Croatian words
|
|
|
|
In: Slovenščina 2.0: Empirične, aplikativne in interdisciplinarne raziskave, Vol 1, Iss 2, Pp 1-34 (2013) (2013)
|
|
Abstract:
Morphological analysis is a prerequisite for many natural language processing tasks. For inflectionally rich languages such as Croatian, morphological analysis typically relies on a morphological lexicon, which lists the lemmas and their paradigms. However, a real-life morphological analyzer must also be able to handle properly the out-of-vocabulary words. We address the task of predicting the correct inflectional paradigm of unknown Croatian words. We frame this as a supervised machine learning problem: we train a classifier to predict whether a candidate lemma-paradigm pair is correct based on a number of string- and corpus-based features. The candidate lemma-paradigm pairs are generated using a handcrafted morphology grammar. Our aim is to examine the machine learning aspect of the problem: we test a comprehensive set of features and evaluate the classification accuracy using different feature subsets. We show that satisfactory classification accuracy (92%) can be achieved with SVM using a combination of string- and corpus-based features. On a per word basis, the F1-score is 53% and accuracy is 70%, which outperforms a frequency-based baseline by a wide margin. We discuss a number of possible directions for future research.
|
|
Keyword:
computational morphology; feature selection; machine learning; P1-1091; paradigm prediction; Philology. Linguistics
|
|
URL: https://doaj.org/article/551d6bbf10e44d5c994ee309ea9a31c5
|
|
BASE
|
|
Hide details
|
|
|
|