Paragraph extraction is a main part of an automatic question answering system, especially in answering why-question. It is because the answer of a why-question usually contained in one paragraph instead of one or two sentences. There have been some researches on paragraph extraction approaches, but there are still few studies focusing on involving the domain ontology as a knowledge base. Most of the paragraph extraction studies used keyword-based method with small portion of semantic approaches. Thus, the question answering system faces a typical problem often occuring in keyword-based method that is word mismatches problem. The main contribution of this research is a paragraph scoring method that incorporates the TFIDF-based and causality-detection-based similarity. This research is a part of the ontology-based why-question answering method, where ontology is used as a knowledge base for each steps of the method including indexing, question analyzing, document retrieval, and paragraph extraction/selection. For measuring the method performance, the evaluations were conducted by comparing the proposed method over two baselines methods that did not use causality-detection-based similarity. The proposed method shown improvements over the baseline methods regarding MRR (95%, 0.82-0.42), P@1 (105%, 0.78-0.38), P@5(91%, 0.88-0.46), Precision (95%, 0.80-0.41), and Recall (66%, 0.88-0.53).
ConvKN at SemEval-2016 Task 3: Answer and Question Selection for Question Answering on Arabic and English Fora
