|
|
|
| Named Entity Recognition Using Linked Data |
| Liu Xiaojuan, Liu Qun, Yu Mengxia |
| School of Government, Beijing Normal University, Beijing 100875 |
|
|
|
|
Abstract Named Entity Recognition (NER) is a basic task in the field of Natural Language Processing with generalized applications. Because of plentiful semantic knowledge, Linked Data can improve the performance of NER. This paper realizes a configurable NER System called NERULD （Named Entity Recognition Using Linked Data） that can support Chinese and English texts and is based on Linked Data in order to disambiguate the recognized entities and to extend the results of NER, so that a new idea to improve the performance of NER can be provided. This study was conducted as follows. We first built a cross-domain Chinese named entity dictionary and English named entity dictionary using the DBpedia dataset. We then designed a distributed model based on Hive and Hadoop to organize, store, and extend Linked Data. We developed a graph-based algorithm to recognize and disambiguate named entities, which can make full use of the semantic relationships of Linked Data. We also tested our algorithm using the DBpedia Spotlight NER Corpus, and compared our result with DBpedia Spotlight, NERSO, and Zemanta, and found that the algorithm implemented in this paper has better performance in recall, precision, and F value.
|
|
Received: 03 August 2018
|
|
|
|
[1] Fafalios P, Baritakis M, Tzitzikas Y. Configuring named entity extraction through real-time exploitation of linked data[C]// Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics. New York: ACM Press, 2014: Article No. 10.
[2] Mendes P N, Jakob M, García-Silva A, et al. DBpedia spotlight: shedding light on the web of documents[C]// Proceedings of the 7th International Conference on Semantic Systems. New York: ACM Press, 2011: 1-8.
[3] Hakimov S, Oto S A, Dogdu E. Named entity recognition and disambiguation using linked data and graph-based centrality scoring[C]// Proceedings of the 4th International Workshop on Semantic Web Information Management. New York: ACM Press, 2012: Article No. 4.
[4] Yosef M A, Hoffart J, Bordino I, et al. Aida: An online tool for accurate disambiguation of named entities in text and tables[J]. Proceedings of the VLDB Endowment, 2011, 4(12): 1450-1453.
[5] Usbeck R, Ngomo A C N, R?der M, et al. AGDISTIS-graph-based disambiguation of named entities using linked data[C]// Proceedings of the International Semantic Web Conference. Heidelberg: Springer, 2014: 457-471.
[6] Gangemi A, Presutti V, Reforgiato Recupero D, et al. Semantic web machine reading with FRED[J]. Semantic Web, 2017, 8(6): 873-893.
[7] Nebhi K. Ontology-based information extraction from Twitter[C]// Proceedings of the Workshop on Information Extraction and Entity Analytics on Social Media Data, Mumbai, India, 2012: 17-22.
[8] Maynard D, Peters W, Li Y Y. Evaluating evaluation metrics for ontology-based applications: Infinite reflection[C]// Proceedings of the International Conference on Language Resources and Evaluation, Marrakech, Morocco, 2010: 1045-1050.
[9] Damljanovic D, Bontcheva K. Named entity disambiguation using linked data[C]// Proceedings of the 9th Extended Semantic Web Conference. 2012: 231-240.
[10] Sinha R, Mihalcea R. Unsupervised graph-based word sense disambiguation using measures of word semantic similarity[C]//Proceedings of the International Conference on Semantic Computing, 2007, 7: 363-369.
[11] Nebhi K. Named entity disambiguation using freebase and syntactic parsing[C]// Proceedings of the First International Conference on Linked Data for Information Extraction. Aachen: CEUR-WS, 2013, 1057: 50-55.
[12] Usbeck R, Ngomo A C N, Luo W C, et al. Multilingual disambiguation of named entities using linked data[C]// Proceedings of the 2014 International Conference on Posters & Demonstrations Track. Aachen: CEUR-WS, 2014, 1272: 101-104. |
|
|
|
