ECNU at 2016 LiveQA Track: A Parameter Sharing Long Short Term Memory Model for Learning Question Similarity

In this paper, we present our system which is evaluated in the TREC 2016 LiveQA Challenge. Same as the last year, the TREC 2016 LiveQA track focuses on “live” question answering for the real-user questions from Yahoo! Answer. In this year, we first apply a parameter sharing Long Short Term Memory(LSTM) network to learn a high embedding of question representation. Then we combine the question representation with the key words information to strengthen the representation of semantic-similar questions, followed by calculating the question similarity with a simple metric function. Our approach outperforms the average score of all submitted runs.