Towards a Framework for an Indonesian Medical Question Generator

Question generating is the task of automatically generating questions from various inputs such as raw text, database, or semantic representation. In this paper, we attempt to describe a general framework that could help develop and characterise efforts to Indonesian medical questions generation. We propose a new style of question generation that actively uses sentences within a document as a source of answers. We use manually written rules to perform a sequence of general purpose syntactic transformations (e.g. identification of keywords or key phrases to NER based on PICO frame) to turn a declarative sentence into questions. The final result of this research is a pattern of question and answer pairs, where the test results show the pattern matching algorithm precision value of 0.101 and a recall of 0.712.