YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations

“Multi-choice Question Answering in Exams” is a typical question answering task, which aims to test how accurately the participants could answer the questions in exams. Most of the existing QA systems typically rely on handcrafted features and rules to conduct question understanding and/or answer ranking. In this paper, we perform convolutional neural networks (CNN) to learn the joint representations of question-answer pairs first, then use the joint representations as the inputs of the long short-term memory (LSTM) with attention to learn the answer sequence of a question for labeling the matching quality of each answer. All questions are restrained within the elementary and middle school level. We also incorporating external knowledge by training Word2Vec on Flashcards data, thus we get more compact embedding. Experimental results show that our method achieves better or comparable performance compared with the baseline system. The proposed approach achieves the accuracy of 0.39, 0.42 in English valid set, test set, respectively.