Question Similarity Calculation for FAQ Answering

Frequently asked question (FAQ) answering is a very useful module in automatic question answering (QA) systems where calculation of question similarity is a key problem. In this paper, we propose a new method for measuring the similarity between users' questions and the questions in a FAQ database. Both statistic measure and semantic information are employed. Statistic similarity is calculated based on dynamically formed vectors while semantic similarity is calculated by utilizing word similarity based on WordNet. Overall similarity is a combination of statistic similarity and semantic similarity. Preliminary results show that our method achieves a good performance.