FootbOWL: Using a Generic Ontology of Football Competition for Planning Match Summaries Nadjet Bouayad-Agha 1 , Gerard Casamayor 1 , Leo Wanner 1,2 , Fernando D´ıez 3 , and Sergio L´ opez Hern´andez 3 1 DTIC, University Pompeu Fabra, Barcelona, Spain firstname.lastname@upf.edu 2 Catalan Institute for Research and Advanced Studies (ICREA) firstname.lastname@icrea.es 3 DII, Universidad Aut´onoma de Madrid, Madrid, Spain firstname.lastname@uam.es Abstract. We present a two-layer OWL ontology-based Knowledge Base (KB) that allows for flexible content selection and discourse struc- turing in Natural Language text Generation (NLG) and discuss its use for these two tasks. The first layer of the ontology contains an application- independent base ontology. It models the domain and was not designed with NLG in mind. The second layer, which is added on top of the base ontology, models entities and events that can be inferred from the base ontology, including inferable logico-semantic relations between individ- uals. The nodes in the KB are weighted according to learnt models of content selection, such that a subset of them can be extracted. The ex- traction is done using templates that also consider semantic relations between the nodes and a simple user profile. The discourse structuring submodule maps the semantic relations to discourse relations and forms discourse units to then arrange them into a coherent discourse graph. The approach is illustrated and evaluated on a KB that models the First Spanish Football League. 1 Introduction Natural language generators typically use as input external or purpose-built do- main databases (DBs) or knowledge bases (KBs), extracting and/or transform- ing the relevant content during the text planning phase to instantiate schemas or other discourse representations, which are then verbalized during linguistic generation. See, for instance, [9]. More recent statistical, or heuristic-based, text planning tends to draw upon KBs crafted specifically for the task of Natural Language Generation (NLG) in order to assess relevance of its parts for inclu- sion into the text plan; see, among others, [4,5]. Given the NLG-tuned nature of these KBs, the mapping from knowledge to linguistic representations is then quite straightforward. G. Antoniou et al. (Eds.): ESWC 2011, Part I, LNCS 6643, pp. 230–244, 2011. c  Springer-Verlag Berlin Heidelberg 2011