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.

[1]  Bowen Zhou,et al.  Applying deep learning to answer selection: A study and an open task , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[2]  Lei Yu,et al.  Deep Learning for Answer Sentence Selection , 2014, ArXiv.

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Daniel Marcu,et al.  A Noisy-Channel Approach to Question Answering , 2003, ACL.

[5]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[6]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[7]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[8]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[9]  Xuchen Yao,et al.  Freebase QA: Information Extraction or Semantic Parsing? , 2014, ACL 2014.

[10]  Xiaoyan Zhu,et al.  Using Conditional Random Fields to Extract Contexts and Answers of Questions from Online Forums , 2008, ACL.

[11]  Xuchen Yao,et al.  Information Extraction over Structured Data: Question Answering with Freebase , 2014, ACL.

[12]  Yi Yang,et al.  WikiQA: A Challenge Dataset for Open-Domain Question Answering , 2015, EMNLP.

[13]  Jason Weston,et al.  Open Question Answering with Weakly Supervised Embedding Models , 2014, ECML/PKDD.

[14]  Nikhil Ketkar,et al.  Convolutional Neural Networks , 2021, Deep Learning with Python.

[15]  Lin Sun,et al.  Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities , 2010, ACL.

[16]  Ming Zhou,et al.  Extracting Chatbot Knowledge from Online Discussion Forums , 2007, IJCAI.

[17]  Alessandro Moschitti,et al.  Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks , 2016, ArXiv.

[18]  Hae-Chang Rim,et al.  Joint Relational Embeddings for Knowledge-based Question Answering , 2014, EMNLP.

[19]  Xiaolong Wang,et al.  Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering , 2015, ACL.

[20]  Xin Jiang,et al.  Neural Generative Question Answering , 2015, IJCAI.