Abstract
We study how to improve the performance of Question Answering over Knowledge Base (KBQA) by utilizing the factoid Question Generation (QG) in this paper. The task of question generation (QG) is to generate a corresponding natural language question given the input answer, while question answering (QA) is a reverse task to find a proper answer given the question. For the KBQA task, the answer could be regarded as a fact containing a predicate and two entities from the knowledge base. Training an effective KBQA system needs a lot of labeled data which are hard to acquire. And a trained KBQA system still performs poor when answering the questions corresponding with unseen predicates in the training process. To solve these challenges, we propose a unified framework to combine the QG and QA with the help of knowledge base and text corpus. The models of QA and QG are first trained jointly on the gold dataset, then the QA model is fine tuned by utilizing a supplemental dataset constructed by the QG model with the help of text evidence. We conduct experiments on two datasets SimpleQuestions and WebQSP with the Freebase knowledge base. Empirical results show that our framework improves the performance of KBQA and performs comparably with or even better than the state-of-the-arts.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
According to the Law of Large Numbers, the frequency can represent the probability if the sample space is large enough.
- 2.
Note that in this process the QA and QG models could be trained utilizing the dual learning framework.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR abs/1409.0473 (2014)
Bordes, A., Usunier, N., Chopra, S., Weston, J.: Large-scale simple question answering with memory networks. CoRR abs/1506.02075 (2015)
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of NIPS (2013)
Dong, L., Lapata, M.: Language to logical form with neural attention. In: Proceedings of ACL (2016)
Dong, L., Mallinson, J., Reddy, S., Lapata, M.: Learning to paraphrase for question answering. In: Proceedings of EMNLP, pp. 875–886 (2017)
ElSahar, H., Gravier, C., Laforest, F.: Zero-shot question generation from knowledge graphs for unseen predicates and entity types. In: Proceedings of NAACL-HLT, pp. 218–228 (2018)
Hu, S., Zou, L., Yu, J.X., Wang, H., Zhao, D.: Answering natural language questions by subgraph matching over knowledge graphs. Trans. Knowl. Data Eng. 30(5), 824–837 (2018)
Hu, S., Zou, L., Zhang, X.: A state-transition framework to answer complex questions over knowledge base. In: Proceedings of EMNLP, pp. 2098–2108 (2018)
Liu, C., He, S., Liu, K., Zhao, J.: Curriculum learning for natural answer generation. In: Proceedings of IJCAI, pp. 4223–4229 (2018)
Luong, T., Sutskever, I., Le, Q.V., Vinyals, O., Zaremba, W.: Addressing the rare word problem in neural machine translation. In: Proceedings of ACL (2015)
Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of ACL, pp. 1003–1011 (2009)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of EMNLP, pp. 1532–1543 (2014)
Serban, I.V., et al.: Generating factoid questions with recurrent neural networks: the 30 m factoid question-answer corpus. In: Proceedings of ACL (2016)
Tang, D., Duan, N., Qin, T., Zhou, M.: Question answering and question generation as dual tasks. CoRR abs/1706.02027 (2017)
Yang, Y., Chang, M.: S-MART: novel tree-based structured learning algorithms applied to tweet entity linking. In: Proceedings of ACL, pp. 504–513 (2015)
Yang, Z., Hu, J., Salakhutdinov, R., Cohen, W.W.: Semi-supervised QA with generative domain-adaptive nets. In: Proceedings of ACL, pp. 1040–1050 (2017)
Yih, W., Chang, M., He, X., Gao, J.: Semantic parsing via staged query graph generation: question answering with knowledge base. In: ACL (2015)
Yih, W., Richardson, M., Meek, C., Chang, M., Suh, J.: The value of semantic parse labeling for knowledge base question answering. In: Proceedings of ACL (2016)
Yin, W., Yu, M., Xiang, B., Zhou, B., Schütze, H.: Simple question answering by attentive convolutional neural network. In: COLING, pp. 1746–1756 (2016)
Yu, L., Hermann, K.M., Blunsom, P., Pulman, S.: Deep learning for answer sentence selection. CoRR abs/1412.1632 (2014)
Yu, M., Yin, W., Hasan, K.S., dos Santos, C.N., Xiang, B., Zhou, B.: Improved neural relation detection for knowledge base question answering. In: Proceedings of ACL (2017)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of ACL (2016)
Acknowledgments
This work was supported by The National Key Research and Development Program of China under grant 2018YFB1003504 and NSFC under grant 61961130390, 61622201 and 61532010.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, S., Zou, L., Zhu, Z. (2019). How Question Generation Can Help Question Answering over Knowledge Base. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11838. Springer, Cham. https://doi.org/10.1007/978-3-030-32233-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-32233-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32232-8
Online ISBN: 978-3-030-32233-5
eBook Packages: Computer ScienceComputer Science (R0)
