Abstract：The existence of ambiguity makes the entity linking task demand a large amount of information. Previous researches mainly uses two types of information, i.e., the information of the text containing the given mention and the external knowledge base. There are still two issues should be addressed. Firstly, current entity linking models have not benefited from the latest knowledge base, which has larger scale and wider coverage. Secondly, the text contains rich information including local context information of the mention and global information such as text topic. The combination approach of local and global information can be further improved. For the first problem, an entity candidate extraction approach considering both text relevance and prior knowledge is proposed to get the effective entity candidate set. For the second problem, a neural network with self-attention and highway network is proposed to represent both local and global information for entity linking. Experiments on six public datasets of entity linking show the effectiveness of our proposed approach. Furthermore, our system achieves the state-of-the-art performance using the latest general knowledge base.
[1] Yih W, Chang M W, He X, et al. Semantic parsing via staged query graph generation: Question answering with knowledge base[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015: 1321-1331. [2] Ji H, Nothman J, Hachey B, et al. Overview of TAC-KBP2015 trilingual entity discovery and linking[C]//Proceedings of the TAC, 2015. [3] Ji H, Nothman J, Dang H T, et al. Overview of TAC-KBP2016 trilingual EDL and its impact on end-to-end Cold-Start KBP[C]//Proceedings of TAC, 2016. [4] Hoffmann R, Zhang C, Ling X, et al. Knowledge-based weak supervision for information extraction of overlapping relations[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human language technologies-volume 1. Association for Computational Linguistics, 2011: 541-550. [5] Sun Y, Lin L, Tang D, et al. Modeling mention, context and entity with neural networks for entity disambiguation[C]//Proceedings of the 24th International Conference on Artificial Intelligence. 2015: 1333-1339. [6] Francis-Landau M, Durrett G, Klein D. Capturing semantic similarity for entity linking with convolutional neural networks[C]//Proceedings of NAACL-HLT. 2016: 1256-1261. [7] Ganea O E, Hofmann T. Deep joint entity disambiguation with local neural attention[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017: 2619-2629. [8] Le P, Titov I. Improving entity linking by modeling latent relations between mentions[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2018: 1595-1604. [9] Pennington J, Socher R, Manning C. Glove: Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014: 1532-1543. [10] Ceccarelli D, Lucchese C, Orlando S, et al. Learning relatedness measures for entity linking[C]//Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. ACM, 2013: 139-148. [11] Busa-Fekete R, Szarvas G, Elteto T, et al. An apple-to-apple comparison of learning-to-rank algorithms in terms of normalized discounted cumulative gain[C]//Proceedings of the 20th European Conference on Artificial Intelligence (ECAI 2012): Preference Learning: Problems and Applications in AI Workshop. 2012: 242. [12] Yue Y, Finley T, Radlinski F, et al. A support vector method for optimizing average precision[C]//Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2007: 271-278. [13] Spitkovsky V I, Chang A X. A Cross-Lingual dictionary for English wikipedia concepts[C]//Proceedings of the 18th International Conference on Language Resources and Evaluation (LREC-2012). 2012: 3168-3175. [14] Hoffart J, Yosef M A, Bordino I, et al. Robust disambiguation of named entities in text[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2011: 782-792. [15] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems, 2017: 6000-6010. [16] Srivastava R K, Greff K, Schmidhuber J. Highway networks[J]. arXiv preprint arXiv: 1505.00387, 2015. [17] 洪铭材, 张阔, 唐杰,等. 基于条件随机场(CRFs)的中文词性标注方法[J]. 计算机科学, 2006, 33(10): 148-151. [18] Wainwright M J, Jordan M I. Graphical Models, Exponential F amilies and Variational Inference[J]. Machine Learning, 2008, 1(1-2): 1-305. [19] Denton E, Weston J, Paluri M, et al. User conditional hashtag prediction for images[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015: 1731-1740. [20] Murphy K P, Weiss Y, Jordan M I. Loopy belief propagation for approximate inference: An empirical study[C]//Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers Inc., 1999: 467-475. [21] Hoffart J, Yosef M A, Bordino I, et al. Robust disambiguation of named entities in text[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2011: 782-792. [22] Guo Z, Barbosa D. Robust named entity disambiguation with random walks[J]. Semantic Web, 2018, 9(4): 459-479. [23] Gabrilovich E, Ringgaard M, Subramanya A. FACC1: Freebase annotation of ClueWeb corpora, Version 1 2013. [24] Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv: 1412.6980, 2014. [25] Chinchor N. MUC-4 evaluation metrics[C]//Proceedings of the 4th Conference on Message Understanding. Association for Computational Linguistics, 1992: 22-29.
2020, Vol. 34 
