Towards a Computational Semantic Analyzer for Urdu
Annette Hautli-Janisz, Miriam Butt · 2011
This paper describes a first approach to a computational semantic analyzer for Urdu on the basis of the deep syntactic analysis done by the Urdu grammar ParGram. Apart from the semantic construction, external lexical resources such as an Urdu WordNet and a preliminary VerbNet style resource for Urdu are developed and connected to the semantic analyzer. These resources allow for a deeper level of representation by providing real-word knowledge such as hypernyms of lexical entities and information on thematic roles. We therefore contribute to the overall goal of providing more insights into the computationally efficient analysis of Urdu, in particular to computational semantic analysis. 1