Abstract
This paper presents a system which learns to answer single-relation questions on a broad range of topics from a knowledge base using a three-layered learning system. Our system first learning a Topic Phrase Detecting model based on a phrase-entities dictionary to detect which phrase is the topic phrase of the question. The second layer of the system learning several answer ranking models. The last layer re-ranking the scores from the output of the second layer and return the highest scored answer. Both convolutional neural networks (CNN) and information retrieval (IR) models are included in this models. Training our system using pairs of questions and structured representations of their answers, yields competitive results on the NLPCC 2016 KBQA share task.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Meeting of the Association for Computational Linguistics (2012)
Yih, W., Chang, M., He, X., et al.: Semantic parsing via staged query graph generation: question answering with knowledge base. In: Meeting of the Association for Computational Linguistics (2015)
Berant, J., Chou, A., Frostig, R., et al.: Semantic parsing on freebase from question-answer Pairs. In: Empirical Methods in Natural Language Processing (2013)
Yao, X., Van Durme, B.: Information extraction over structured data: question answering with freebase. In: Meeting of the Association for Computational Linguistics (2014)
Bast, H., Haussmann, E.: More accurate question answering on freebase. In: Conference on Information and Knowledge Management (2015)
Bordes, A., Chopra, S., Weston, J., et al.: Question answering with subgraph embeddings. In: Empirical Methods in Natural Language Processing (2014)
Dong, L., Wei, F., Zhou, M., et al.: Question answering over freebase with multi-column convolutional neural networks. In: Meeting of the Association for Computational Linguistics (2015)
Fader, A., Zettlemoyer, L., Etzioni, O., et al.: Open question answering over curated and extracted knowledge bases. In: Knowledge Discovery and Data Mining (2014)
Yao, X.: Lean question answering over freebase from scratch. In: North American Chapter of the Association for Computational Linguistics (2015)
Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Meeting of the Association for Computational Linguistics (2014)
Reddy, S., Lapata, M., Steedman, M., et al.: Large-scale semantic parsing without question-answer pairs (2014)
Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Meeting of the Association for Computational Linguistics (2015)
Wang, Y., Berant, J., Liang, P., et al.: Building a semantic parser overnight. In: Meeting of the Association for Computational Linguistics (2015)
Acknowledgment
The work is supported by National Basic Research and Development Program (Nos. 2013CB329601, 2013CB329604) and National Natural Science Foundation of China (No. 61502517, No. 61472433, No. 61372191, No. 61572492).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Yang, F., Gan, L., Li, A., Huang, D., Chou, X., Liu, H. (2016). Combining Deep Learning with Information Retrieval for Question Answering. In: Lin, CY., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds) Natural Language Understanding and Intelligent Applications. ICCPOL NLPCC 2016 2016. Lecture Notes in Computer Science(), vol 10102. Springer, Cham. https://doi.org/10.1007/978-3-319-50496-4_86
Download citation
DOI: https://doi.org/10.1007/978-3-319-50496-4_86
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50495-7
Online ISBN: 978-3-319-50496-4
eBook Packages: Computer ScienceComputer Science (R0)