[GRGC] Daniel Jimenez-Casas (U. Pompeu Fabra)

retour à la page du Séminaire Grammaires créoles

Palenquero 2.0 — Open NLP Strategies for Corpus Building, Parsing, and Text Processing for Palenquero Creole (Colombia)

Daniel Jimenez-Casas (U. Pompeu Fabra)

Palenquero is a Spanish-based endangered creole language from Colombia with very limited resources for applying natural language processing (NLP) techniques. 

The project presented here seeks to promote the digital use of Palenquero and help increase its digital vitality by ensuring the availability of digital language resources and providing the necessary technical support to collect and curate it. Surveying the digital vitality of Palenquero, collecting a corpus, evaluating pipelines for text normalisation, and testing methods for automated part-of-speech tagging and parsing are the core activities of this project. 

As part of the corpus collection and a visiting fellowship project at the Leibniz Centre for General Linguistics (ZAS) in Berlin, I am currently using NLP techniques to look into the predicate negation in Palenquero. 

Palenquero features three types negation: preverbal, pre- and postverbal, and strictly postverbal. This last form is the most common, a typologically rare feature among the world’s languages and creoles (Dieck, 2000; Schwegler, 2013). Schwegler (1991) suggested the variation had pragmatic causes. However, Dieck (2000, 2002) argued the phenomenon had to do with semantics and morphosyntactic features. 

The discussion is still open and authors do not seem to come to an agreement (Schwegler, 2018). To contribute to the understanding of the predicate negation in Palenquero, I have proposed a corpus-based study with the goal of using natural language processing (NLP) techniques to understand how changes in register may influence the choice of negation patterns in Palenquero and contribute to the computational documentation of this endangered creole language. 

References

Dieck, M. (2000). La negación en palenquero: Análisis sincrónico, estudio comparativo y consecuencias teóricas. Vervuert/Iberoamericana. 
Dieck, M. (2002). Distribución y escopo de la negación en palenquero. In Y. Moñino & A. Schwegler (Eds.), Palenque, Cartagena y Afro-Caribe: Historia y lengua (pp. 149–167). Niemeyer. 
Schwegler, A. (1991). Negation in Palenquero: Synchrony. Journal of Pidgin and Creole Languages, 6 (2), 165–214. https://doi.org/10.1075/jpcl.6.2.02sch 
Schwegler, A. (2013). Palenquero. In S. M. Michaelis, P. Maurer, M. Haspelmath, & M. Huber (Eds.), Atlas of Pidgin and Creole Language Structures (APiCS). Oxford University Press. https://apics-online.info/surveys/48 
Schwegler, A. (2018). Negation in Palenquero: Syntax, pragmatics, and change in progress. In V. Déprez & F. Henri (Eds.), The view from Creoles (pp. 257–288). John Benjamins Publishing Company. https://doi.org/doi: 10.1075/coll.55.12sch