Using frames to infer numerical extracted answers

Question answering (QA) systems and their undeniable usefulness become more and more obvious nowadays. There are situations where the QA systems are not able to extract a concise and salient answer to a given question. A long descriptive answer instead of a concise one can affect the efficiency of the system. The main aim of this research is on producing a concise answer from the set of retrieved answers given by any QA system. We particularly focus on the situations when the correct answer has to be a numerical value. In this paper, we will demonstrate a nearly new data structure called frame. A frame will be constructed for each of the numerical values that are within the answer set. Our method uses natural language processing techniques in addition to information extraction techniques to fill in the frames. The evaluation of the constructed frames shows acceptable results.