Abstract
Named entity discovery and linking is the fundamental and core component of question answering. In Question Entity Discovery and Linking (QEDL) problem, traditional methods are challenged because multiple entities in one short question are difficult to be discovered entirely and the incomplete information in short text makes entity linking hard to implement. To overcome these difficulties, we proposed a knowledge graph based solution for QEDL and developed a system consists of Question Entity Discovery (QED) module and Entity Linking (EL) module. The method of QED module is a tradeoff and ensemble of two methods. One is the method based on knowledge graph retrieval, which could extract more entities in questions and guarantee the recall rate, the other is the method based on Conditional Random Field (CRF), which improves the precision rate. The EL module is treated as a ranking problem and Learning to Rank (LTR) method with features such as semantic similarity, text similarity and entity popularity is utilized to extract and make full use of the information in short texts. On the official dataset of a shared QEDL evaluation task, our approach could obtain 64.44% F1 score of QED and 64.86% accuracy of EL, which ranks the 2nd place and indicates its practical use for QEDL problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chinchor, N.: MUC7 named entity task definition. In: MUC (1997)
Han, X., Sun, L.: A generative entity-mention model for linking entities with knowledge base. In: ACL, pp. 945–954 (2011)
Humphreys, R.G., Azzam, S., Huyck, C., Mitchell, B., Cunningham, H., Wilks, Y.: Description of the LaSIE-II System as Used for MUC7, pp. 127–140 (1998)
Fu, G., Luke, K.K.: Chinese named entity recognition using lexicalized HMMs. ACM SIGKDD Explor. Newsl. 7(1), 19–25 (2005)
Hai, L.C., Ng, H.T.: Named entity recognition: a maximum entropy approach using global information. In: COLING, pp. 1–7 (2002)
Li, L., Mao, T., Huang, D., Yang, Y.: Hybrid models for Chinese named entity recognition. In: Proceedings of SIGHAN Workshop, pp. 72–78 (2006)
Chen, A., Peng, F., Shan, R., Sun, G.: Chinese named entity recognition with conditional probabilistic models, pp. 173–176 (2006)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. Comput. Sci. (2015)
Chiu, J. P. C., Nichols, E.: Named entity recognition with bidirectional LSTM-CNNs. Comput. Sci. (2015)
Zheng, Z., Li, F., Huang, M., Zhu, X.: Learning to link entities with knowledge base. In: NAACL, pp. 483–491 (2010)
Hoffart, J., Yosef, M.A., Bordino, I., Fürstenau, H., Pinkal, M., Spaniol, M.: Robust disambiguation of named entities in text. In: EMNLP, pp. 782–792 (2011)
Mihalcea, R., Csomai, A.: Wikify! linking documents to encyclopedic knowledge. In: CIKM, pp. 233–242 (2007)
Cucerzan, S.: Large-scale named entity disambiguation based on wikipedia data. In: EMNLP-CoNLL, pp. 708–716 (2007)
Golub, D., He, X.: Character-level question answering with attention. In: Proceedings of EMNLP, pp. 1598–1607 (2016)
Han, S., Zhang, Y., Ma, Y.: THUOCL: Tsinghua open Chinese lexicon (2016)
Kenter, T., Rijke, M.D.: Short text similarity with word embeddings. In: CIKM, pp. 1411–1420 (2015)
Robertson, S., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends® Inf. Retr. 3(4), 333–389 (2009)
Xu, W.: A Chinese keyword extraction algorithm based on TFIDF method. Inf. Stud. Theory Appl. (2008)
Mirzal, A.: Similarity-based matrix completion algorithm for latent semantic indexing. In: IEEE ICCSCE, pp. 79–84 (2014)
Celikyilmaz, A., Hakkani-Tur, D., Tur, G.: LDA based similarity modeling for question answering. In: Proceedings of the NAACL HLT Workshop, pp. 1–9 (2010)
Acknowledgement
This work was financially supported by the National Natural Science Foundation of China (No. 61602013), and the Shenzhen Key Fundamental Research Projects (Grant Nos. JCYJ20160330095313861, JCYJ20151030154330711 and JCYJ20151014093505032).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Lei, K., Zhang, B., Liu, Y., Deng, Y., Zhang, D., Shen, Y. (2018). A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions. In: Qiu, M. (eds) Smart Computing and Communication. SmartCom 2017. Lecture Notes in Computer Science(), vol 10699. Springer, Cham. https://doi.org/10.1007/978-3-319-73830-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-73830-7_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73829-1
Online ISBN: 978-3-319-73830-7
eBook Packages: Computer ScienceComputer Science (R0)