{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:11:08Z","timestamp":1781107868368,"version":"3.54.1"},"reference-count":25,"publisher":"IGI Global Scientific Publishing","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,1]]},"abstract":"<p>Chinese word segmentation is the basis of the Chinese natural language processing (NLP). With the development of the deep learning, various neural network models are applied to the Chinese word segmentation. However, current neural network models have the characteristics of artificial feature extraction, nonstandard word-weight, inability to effectively use long-distance information and long training time of models in Chinese word segmentation. To solve a series of problems, this article presents a CNN-Bidirectional GRU-CRF neural network model (CNN Bidirectional GRU CRF Network, CBiGCN), which breaks through the limit of conventional method window, truly realizes end-to-end processing and applies to the neural network model by the five-Tag set method, bias-variable-weight greedy strategy and supplements by Goldstein-Armijo guidelines. Besides, this model, with simple structure, is easy to be operated. And it can automatically learn features, reduces large amounts of tasks on specific knowledge in the form of handcrafted features and data pre-processing, makes use of context information effectively. The authors set an experiment with two data corpuses for Chinese word segmentation to evaluate their system. The experiment verified their new model can obtain better Chinese word segmentation results and greatly reduce training time.<\/p>","DOI":"10.4018\/ijthi.2019070104","type":"journal-article","created":{"date-parts":[[2019,4,15]],"date-time":"2019-04-15T14:49:22Z","timestamp":1555339762000},"page":"47-62","source":"Crossref","is-referenced-by-count":9,"title":["Learning Chinese Word Segmentation Based on Bidirectional GRU-CRF and CNN Network Model"],"prefix":"10.4018","volume":"15","author":[{"given":"Chenghai","family":"Yu","sequence":"first","affiliation":[{"name":"Zhejiang Sci-Tech University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shupei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2432","reference":[{"key":"IJTHI.2019070104-0","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.122"},{"key":"IJTHI.2019070104-1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1141"},{"key":"IJTHI.2019070104-2","unstructured":"Chinese Information Society. (2016). Chinese Information Processing Development Report. Retrieved from http:\/\/www.cipsc.org.cn\/"},{"key":"IJTHI.2019070104-3","unstructured":"CSDN.net. (n.d.). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[OL]. Retrieved from http:\/\/blog.csdn.net\/meanme\/article\/details\/48845793"},{"issue":"5","key":"IJTHI.2019070104-4","first-page":"101","article-title":"Novel conditional random field model extended by tensor and its application in natural language processing tasks.","volume":"33","author":"Y.Feng","year":"2016","journal-title":"Jisuanji Yingyong Yanjiu"},{"key":"IJTHI.2019070104-5","unstructured":"Han, D. & Chang, B. (2015). Approaches to Domain Adaptive Chinese Segmentation Model. Chinese Journal of Computers, 38(2), 35-45."},{"issue":"5","key":"IJTHI.2019070104-6","first-page":"962","article-title":"Dual-Layer CRFs Based on Subword for Chinese Word Segmentation.","volume":"47","author":"D.Huang","year":"2010","journal-title":"Journal of Computer Research and Development"},{"key":"IJTHI.2019070104-7","first-page":"260","article-title":"Neural Architectures for Named Entity Recognition.","author":"G.Lample","year":"2016","journal-title":"Proceedings of NAACL-HLT 2016"},{"key":"IJTHI.2019070104-8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.046"},{"issue":"1","key":"IJTHI.2019070104-9","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1080\/13658816.2017.1379084","article-title":"A hybrid method for Chinese address segmentation.","volume":"32","author":"L.Li","year":"2018","journal-title":"International Journal of Geographical Information Science"},{"issue":"2","key":"IJTHI.2019070104-10","first-page":"237","article-title":"A Gated Recurrent Unit Neural Network for Chinese Word Segmentation.","volume":"56","author":"X.Li","year":"2017","journal-title":"Journal of Xiamen University"},{"issue":"8","key":"IJTHI.2019070104-11","first-page":"30","article-title":"Chinese word segmentation method for short Chinese text based on conditional random fields.","volume":"55","author":"Z.Liu","year":"2015","journal-title":"Journal of Tsinghua University"},{"key":"IJTHI.2019070104-12","unstructured":"Lu, X., Xu, Y., Deng, W., & Yan, Y. (2016). Decryption of Full Text Retrieval Technology: Chinese Word Segmentation. In The 2nd International Conference on Materials Engineering and Information Technology Applications (MEITA 2016) (pp. 334-337). Atlantis Press."},{"key":"IJTHI.2019070104-13","doi-asserted-by":"crossref","unstructured":"Ma, X., & Hovy, E. (2016). End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin (pp. 130-136).","DOI":"10.18653\/v1\/P16-1101"},{"key":"IJTHI.2019070104-14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1028"},{"key":"IJTHI.2019070104-15","unstructured":"Ren, Z., Xu, H., Feng, S., Zhou, H. & Shi, J. (2017). Sequence labeling Chinese word segmentation method based on LSTM networks. Application Research of Computers, 34(5), 4-9."},{"key":"IJTHI.2019070104-16","doi-asserted-by":"crossref","unstructured":"Su, T., Jia, S., Wang, Q., Sun, L., & Wang, R. (2017). Novel character segmentation method for overlapped Chinese handwriting recognition based on LSTM neural networks. In 2016 23rd International Conference on Pattern Recognition. Mexico, International Conference on Pattern Recognition (pp. 1141-1146). Retrieved from http:\/\/sighan.cs.uchicago.edu\/bakeoff2005\/","DOI":"10.1109\/ICPR.2016.7899790"},{"key":"IJTHI.2019070104-17","unstructured":"Wan, S., Lan, Y., Guo, J., Xu, J., Pang, L. & Cheng, X. (2017). Local Bidirectional Long Short Term Memory for Text Classification. Journal of Chinese Information Processing, 31(3), 62-68."},{"key":"IJTHI.2019070104-18","unstructured":"Wang, W., Mu, X. & Wang, L. (2017). An Approach for Chinese Word Segmentation Based on Feature Embedding Neural Network. Journal of South-Central University for Nationalities (Nat Sci. Edition), 36(1), 102-106."},{"issue":"10","key":"IJTHI.2019070104-19","first-page":"1445","article-title":"A Survey on Deep Learning for Natural Language Processing.","volume":"42","author":"X.Xi","year":"2016","journal-title":"ACTA AUTOMATICA SINICA"},{"key":"IJTHI.2019070104-20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2092"},{"key":"IJTHI.2019070104-21","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-016-0506-8"},{"key":"IJTHI.2019070104-22","doi-asserted-by":"crossref","unstructured":"Yao, Y., & Huang, Z. (2016). Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation. International Conference on Neural Information Processing 2016. Neural Information Processing, 345-353","DOI":"10.1007\/978-3-319-46681-1_42"},{"key":"IJTHI.2019070104-23","author":"Z.Zhang","year":"2017","journal-title":"Chinese Word Segmentation Based on Bi-directional LSTM-CRF Model. Journal of Changchun University of Science and Technology"},{"key":"IJTHI.2019070104-24","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2016.0029"}],"container-title":["International Journal of Technology and Human Interaction"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=227401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T11:53:26Z","timestamp":1651838006000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJTHI.2019070104"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2019,7,1]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,7]]}},"URL":"https:\/\/doi.org\/10.4018\/ijthi.2019070104","relation":{},"ISSN":["1548-3908","1548-3916"],"issn-type":[{"value":"1548-3908","type":"print"},{"value":"1548-3916","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,1]]}}}