A Comparison of Data-Driven Automatic Syllabification Methods
SPIRE '09 Proceedings of the 16th International Symposium on String Processing and Information Retrieval
Finding spanish syllabification rules with decision trees
FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing
A morphological analyzer using hash tables in main memory (MAHT) and a lexical knowledge base
CICLing'12 Proceedings of the 13th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part I
Hi-index | 12.05 |
The syllabification of Spanish's words follows a few basic rules, but the syllabification of some words deviates from the general rules according to a number of factors described in this paper. Prefixes are major cause of variations on syllabification. Since, in Spanish, prefixes tend to do not integrate into other syllables when they are prominent, the syllabification of words can vary depending on the prominence of the prefixes. This paper shows that, in many cases, the prominence of a prefix can be inferred by means of some morphological and lexical knowledge. This paper proposes a syllabification algorithm that implements the basic syllabification rules and combines them with morphological and lexical information obtained from three sources: a lemmatizer, a derivation database, and the Corpus de Referencia del Espanol Actual (CREA) of Royal Spanish Academy. Using this additional information, this paper attempts to provide a solution to the problem of taken into account the prefixes according to its prominence for a correct syllabification.