Analysing the Integration of Semantic Web Features for Document Planning across Genres

Language is usually studied and analysed from different disciplines generally on the premise that it constitutes a form of communication which pursues a specific objective. The discourse, in that sense, can be understood as a text which is constructed to express such objective. When a discourse is created, its production is related to some textual genre, usually connected with some pragmatic features, like the intention of the writer or the audience to whom is addressed, both conditioning the use of language. But genres can be considered as well as compounds of different pieces of text with a certain degree of order, each one seeking for more concrete objectives. This paper presents a proposal to learn such features as a way to generate richer document plans, applying clustering techniques over annotated documents.

Autores: 
Vicente, Marta
Lloret, Elena
Tipo de publicación: 
Acta de congreso
Nombre de la revista: 
-
Nombre del libro: 
2nd International Workshop on Natural Language Generation and the Semantic Web
Subtítulo: 
WebNLG
Revisión por pares: 
Internacional: 
Publicable: 
Año de publicación: 
2 016