Recurrent convolutional neural network for answer selection in community question answering

Abstract In this paper, we propose a recurrent convolutional neural network (RCNN) for answer selection in community question answering (CQA). It combines convolutional neural network (CNN) with recurrent neural network (RNN) to capture both the semantic matching between question and answer and the semantic correlations embedded in the sequence of answers. Firstly, the representations of question and answer are learnt separately via CNNs. Then a fully connected neural network is used to generate the fixed length representation for each question–answer (QA) pair. The sequence of QA pair representations are then fed into the RNNs to model the semantic correlations among answers. Finally, the softmax classifier is used to identify the matching quality of answers for a given question. In order to further improve the sequence learning capability, a two-phrases learning strategy is designed to train the model, which fine-tunes the RNNs with the learnt context-dependent representations. Results show that, RCNN can improve the Macro-F1 by 2.75% over the baseline model that is based on two parallel CNNs. By integrating thread-level features into QA matching, our model achieves the best performance of Macro-F1 58.77%, which is 1.6% higher than the best submitted system of the answer selection task in SemEval2015. The results prove the effectiveness of the proposed model on the task of answer selection in CQA.

[1]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[2]  Ming Liu,et al.  Multimodal DBN for Predicting High-Quality Answers in cQA portals , 2013, ACL.

[3]  Preslav Nakov,et al.  SemEval-2015 Task 3: Answer Selection in Community Question Answering , 2015, *SEMEVAL.

[4]  Ming-Wei Chang,et al.  Question Answering Using Enhanced Lexical Semantic Models , 2013, ACL.

[5]  Christopher Meek,et al.  Semantic Parsing for Single-Relation Question Answering , 2014, ACL.

[6]  W. Bruce Croft,et al.  Retrieval models for question and answer archives , 2008, SIGIR '08.

[7]  Tat-Seng Chua,et al.  Question answering passage retrieval using dependency relations , 2005, SIGIR '05.

[8]  Jun Guo,et al.  An empirical convolutional neural network approach for semantic relation classification , 2016, Neurocomputing.

[9]  Noah A. Smith,et al.  What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA , 2007, EMNLP.

[10]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[11]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[12]  Roberto Basili,et al.  Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification , 2007, ACL.

[13]  Steffen Udluft,et al.  Learning long-term dependencies with recurrent neural networks , 2008, Neurocomputing.

[14]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[15]  Yi Yang,et al.  Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited Supervision , 2015, ACM Multimedia.

[16]  Noah A. Smith,et al.  Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions , 2010, NAACL.

[17]  Daniel Jurafsky,et al.  A Hierarchical Neural Autoencoder for Paragraphs and Documents , 2015, ACL.

[18]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

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

[20]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[21]  Young-In Song,et al.  Finding question-answer pairs from online forums , 2008, SIGIR '08.

[22]  Kai Wang,et al.  A syntactic tree matching approach to finding similar questions in community-based qa services , 2009, SIGIR.

[23]  Alessandro Moschitti,et al.  Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks , 2015, SIGIR.

[24]  Jun Zhao,et al.  Recurrent Convolutional Neural Networks for Text Classification , 2015, AAAI.

[25]  Yi Liu,et al.  Statistical Machine Translation for Query Expansion in Answer Retrieval , 2007, ACL.

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

[27]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[28]  Peng Wang,et al.  Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification , 2016, Neurocomputing.

[29]  W. Bruce Croft,et al.  Finding similar questions in large question and answer archives , 2005, CIKM '05.

[30]  Yi Yang,et al.  Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM , 2015, ICML.

[31]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[32]  Jean Pierre Asselin de Beauville,et al.  Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks , 2002, Neurocomputing.

[33]  Li Cai,et al.  Phrase-Based Translation Model for Question Retrieval in Community Question Answer Archives , 2011, ACL.

[34]  Preslav Nakov,et al.  Thread-Level Information for Comment Classification in Community Question Answering , 2015, ACL.

[35]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[36]  Lin Sun,et al.  Extracting Chinese question-answer pairs from online forums , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

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

[38]  Di Wang,et al.  A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering , 2015, ACL.

[39]  Alessandro Moschitti,et al.  Automatic Feature Engineering for Answer Selection and Extraction , 2013, EMNLP.

[40]  Vibhu O. Mittal,et al.  Bridging the lexical chasm: statistical approaches to answer-finding , 2000, SIGIR '00.

[41]  Hang Li,et al.  Convolutional Neural Network Architectures for Matching Natural Language Sentences , 2014, NIPS.

[42]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[43]  Jeffrey Pomerantz,et al.  Evaluating and predicting answer quality in community QA , 2010, SIGIR.

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

[45]  Chris Callison-Burch,et al.  Answer Extraction as Sequence Tagging with Tree Edit Distance , 2013, NAACL.

[46]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[47]  Masafumi Hagiwara,et al.  Natural language neural network and its application to question-answering system , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[48]  Christopher D. Manning,et al.  Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering , 2010, COLING.

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

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

[51]  Mihai Surdeanu,et al.  Learning to Rank Answers on Large Online QA Collections , 2008, ACL.