Automatically answering repeated questions based on semantic question patterns

An automatic method for answering repeated questions based on semantic question patterns is proposed in this paper. The semantic question pattern used is a generalized representation of a group of questions with both similar structure and relevant semantics. Specifically, it consists of semantic annotations (or constraints) for the variable components in the pattern and hence enhances the semantic representation and greatly reduces the ambiguity of a question instance when asked by a user using such pattern. The proposed method consists of three major steps: structure processing, similar pattern matching and filtering, question similarity evaluation and answer retrieval. Preliminary experiments show that the precision of acquisition of the best answer to a new question can be more than 90% on our testing dataset.