Semantically annotated corpus model of Indonesian Translation of Quran: An effort in increasing question answering system performance

This paper presents our work in defining a model to build a semantic-based corpus of Indonesian Translation of the Quran. This task was being an effort to increase Question Answering System (QAS) performance on Indonesian Translation of the Quran that has been developed in 2013[1]. As the QAS run on three kinds of question type i.e. Siapa (Who), Kapan (When), and Di mana (Where), this model designed specifically to deal with those question types. The model is ready to be implemented and evaluated. Since we want to measure how significance semantic approach is on QAS performance, evaluation will be conducted by using the same scheme used. Furthermore, our model also will be assessed by comparing it with other corpus developed by using graph database model.