Answering learners' questions by retrieving question paraphrases from social Q&A sites

摘要: Information overload is a well-known problem which can be particularly detrimental to learners. In this paper, we propose method support learners in the information seeking process consists answering their questions by retrieving question paraphrases and corresponding answers from social Q&A sites. Given novelty of kind data, it crucial get better understanding how sites automatically analysed retrieved. We discuss evaluate several pre-processing strategies similarity metrics, using new paraphrase corpus collected WikiAnswers site. The results show that viable performance levels more than 80% accuracy obtained for task retrieval.