答案选择是自动问答系统中的关键任务之一,其主要目的是根据问题与候选答案的相似性对候选答案进行排序,并选择出相关性较高的答案返回给用户。可将其看作成一个文本对的匹配问题。该文利用词向量、双向LSTM、2D神经网络等深度学习模型对问题—答案对的语义匹配特征进行了提取,并将其与传统NLP特征相结合,提出一种融合深度匹配特征的答案选择模型。在Qatar Living社区问答数据集上的实验显示,融合深度匹配特征的答案选择模型比基于传统特征的模型MAP值高5%左右。
Abstract
Answer Selection is one of the key tasks in question answering system. Its main purpose is to rank the candidate answers according to the similarity between the questions and the candidate answers and select the more relevant answers to users. It can be seen as a text pair matching problem. In this paper, we use the deeplearning model such as word embedding, bidirectional LSTM, 2D neural network and so on to extract the semantic matching features for question-answer pairs, and incorperate these into a ranking model together with traditonal NLP features. The experiments on the Qatar Living community question answering data show that the answer selection model with deep matching features is about 5% higher than only using traditional features on the MAP values.
关键词
问答系统 /
答案选择 /
深度匹配模型
{{custom_keyword}} /
Key words
question answering /
answer selection /
deep matching model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 庞亮,等. 深度文本匹配综述[J]. 计算机学报,2017,(04):985-1003.
[2] Chen T,Guestrin C. XGBoost:A Scalable Tree Boosting System[C]//Proceedings of the ACM SIGKDD International Conference. ACM,2016:785-794.
[3] Loper E,Bird S. NLTK:the Natural Language Toolkit[C]//Proceedings of the Acl-02 Workshop on Effective TOOLS and Methodologies for Teaching Natural Language Processing and Computational Linguistics. Association for Computational Linguistics,2002:63-70.
[4] Klein D,Manning C D. Accurateunlexicalized parsing[C]//Proceedings of the Meeting on Association for Computational Linguistics. Association for Computational Linguistics,2003:423-430.
[5] Salton G,Buckley C. Term-weightingapproaches in automatic text retrieval[J].Information Processing and Management,1988,24(5):513-523.
[6] Allison L,Dix T I. A bit-string longest-common-subsequencealgorithm[J].Information Processing Letters,1986,23(5):305-310.
[7] Mikolov T,Sutskever I,Chen K,et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the Advances in neural information processing systems,F,2013.
[8] Ikolov T,Yih W-T,Zweig G. Linguistic Regularities in Continuous Space Word Representations[C]//Proceedings of the HLT-NAACL,F,2013.
[9] Graves A. Long Short-Term Memory[M].Supervised Sequence Labelling with Recurrent Neural Networks. Springer Berlin Heidelberg,2012:1735-1780.
[10] Pang L, Lan Y,Guo J,et al. Text Matching as Image Recognition[C]]//AAAI. 2016:2793-2799.
[11] Nair V,Hinton G E. Rectified linear units improve restricted boltzmann machines[C]//Proceedings of International Conference on Machine Learning. Omnipress,2010:807-814.
[12] Nakov P,et al. SemEval-2017 Task 3:Community Question Answering[C]//Proceedings of International Workshop on Semantic Evaluation. 2017.
[13] Duchi J,Hazan E,Singer Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[J].Journal of Machine Learning Research,2011,12(7):2121-2159.
[14] Srivastava N,et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research,2014,15(1):1929-1958.
[15] Caruana R,Lawrence S, Giles C L. Overfitting in neural nets:Backpropagation, conjugate gradient, and early stopping[C]//Proceedings of Advances in neural information processing systems. 2001:402-408.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1745 KB)
