Jerid Francom is currently working with the ACTIV-ES corpus to develop an online interface to facilitate the classification and exploration of documents written in Spanish. Combining the Spanish language data and computational methods from information retrieval, the site will allow the public to upload a document of unknown origin, have that document classified as being from either Argentina, Mexico, or Spain, and then be able to visually identify those linguistic elements that are most and least indicative of the classified document. The aim is to make sophisticated computational tools available to a broad audience and facilitate identification of and bring awareness to dialect-specific and language-general patterns of the Spanish language.

 

Comments are closed.