Paper: Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites

ACL ID W08-0906
Title Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2008
Authors

Information overload is a well-known prob- lem which can be particularly detrimental to learners. In this paper, we propose a method to support learners in the information seek- ing process which consists in answering their questions by retrieving question paraphrases and their corresponding answers from social Q&A sites. Given the novelty of this kind of data, it is crucial to get a better understand- ing of how questions in social Q&A sites can be automatically analysed and retrieved. We discuss and evaluate several pre-processing strategies and question similarity metrics, us- ing a new question paraphrase corpus col- lected from the WikiAnswersQ&A site. The results show that viable performancelevels of more than 80% accuracy can be obtained for the task of questionparaphraseretrieval.