Chinese Shallow Semantic Parsing Based on Multi-method of Machine Learning
Keywords:Semantic role labelling, multi-method, linear sequence, hierarchical tree, deep learning, modularization
With the rapid development of 5G+ information intelligence, higher requirements are put forward for accurate and efficient semantic annotation methods. Semantic role annotation for any single method at present has its obvious and complementary advantages and disadvantages. Therefore, this paper attempts to introduce the above three mainstream and stable annotation methods into each task of semantic role annotation, and designs a Chinese semantic role annotation that integrates multi-method. This method integrates the statistical-based linear sequence method, the rule-based hierarchical tree method and the most advanced deep learning in the four processing modules of semantic role annotation. Multi-level linguistic features are introduced into the feature arrangement of the model to realize the mutual combination of multiple modules. Experiments show that the modular fusion of steps and methods effectively improves the annotation performance of each step of annotation.
F. Huang, K.Papineni. Hierarchical System Combination for Machine Translation// In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Prague: Association for Computational Linguistics, 2007. 277-286
Y.P. Liu, S.Li, T.J.Zhao, Systematic Fusion Based on Word Net Word Sense Disambiguation. Acta Automata Sinica, 2010, 36 (11): 1575-1580.
L.Mdrquez, M.Surdeanu, P.Cmas, et al. A robust combination strategy for semantic role annotation// In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computing Machinery, 2005. 644-651.
M.X. Li, C.Q.Zong, Review of Machine Translation System Fusion Technology. Chinese Journal of Information Technology, 2010, 24 (4): 74-84.
R. Lawrence,Rabiner Digital Speech Processing Theory and Application Beijing. Electronic Industry Press
D. Gildea, D. Jurafsky,Automatic annotation of semantic roles. Computational Linguistics, 2002, 28(3):245-288.
D. Gildea, M.Palmer, The necessity of syntactic parsing for predicate argument recognition//In Proceedings of ACL-2002. Philadelphia, USA, 2002:239-246.
S. Pradhan, K. Hacioglu, V. Krugler, et al. Support vector learning for semantic argument classification. Machine Learning Journal, 2005, 60(1):11-39.
S. Pradhan, W.Ward, K.Hacioglu, et al. Semantic role annotation using different syntactic views//In Proceedings of ACL-2005. Ann Arbor, USA, 2005:581-588.
N. Xue, M. Palmer,Calibrating features for Semantic Role Labelling//In Proceedings of EMNLP-2004. Barcelona, Spain, 2004:88-94.
C. Ronan, W. Jason. A unified architecture for natural language processing: Deep neural networks with multitask learning// Proceedings of the 25th international conference on machine learning. 2008:160-167.
R.Socher, E. Huang, Jeffrey Pennington, et al. Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection// In Proceedings of the NIPS, 2011: 801-809.
W.P.Yin, H.Schutze. Convolutional Neural Network for Paraphrase Identification// In Proceedings of the HLT-NAACL, 2015: 901-911.
S. Narayanan, S. Harabagiu,Question answering based on semantic structures// Proceedings of the 20th International Conference on Computational Linguistics. Geneva, Switzerland, 2004: 693-701.
F.C. Wan,Extracting Algorithm for the Optimum Solution Answer Oriented Towards the Restricted Domain. IPPTA: Quarterly Journal of Indian Pulp and Paper Technical Association. 2018, 30(5):590-597.
H. Zhao, W.L. Chen, C.Kit,Semantic dependency parsing of NomBank and PropBank: an efficient integrated approach via a large-scale feature selection//Proceedings of the CoNLL-2009. Boulder: ACL Press, 2009:30-39.
H.J. Liu, W.X. Che, T.Liu, Feature engineering of Chinese semantic role annotation. Chinese Journal of Information Technology. 2007, 22 (1): 79-84.
Y.D. Chen, T.Wang, H.W.Chen, Shallow semantic analysis of semi-supervised learning and active learning. Chinese Journal of Information Technology, 2008 (02): 70-75.
J.H. Li, R.B. Wang, W.L. Wang, et al. Automatic annotation of semantic roles in Chinese frames. Acta Software Sinica, 2010, 30 (4): 597-611.
J.H. Li,Research on Automatic Annotation Technology of Chinese Frame Semantic Roles. Taiyuan: Shanxi University. 2010.
Y.C. Wang, F.C. Wan, N. Ma,Multi-clue Chinese Semantic Role Annotation Based on Conditional Random Fields. Journal of Yunnan University (Natural Science Edition), 2020, 42 (3): 474-480.
Z. Wang, T.S. Jiang, B.B. Chang, et al. Chinese Semantic Role Annotation with Bidirectional Recurrent Neural Networks// Lisbon, Portugal: Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing, 2015: 1626-1631.
W. Zhen, B.B. Chang, Z.F. Sui,Chinese semantic role annotation based on hierarchical output neural network. Chinese Journal of Information Technology, 2014, 28 (6): 56-61.
M.X. Wang, Liu Q. Semantic role annotation based on deep neural network. Chinese Journal of Information Technology, 2018, 32 (02): 50-57.
T.S. Li, Q.Li, W.H. Wang, B.B. Chang,Text Retelling Discriminant Model Based on External Memory Unit and Semantic Role Knowledge. Chinese Journal of Information Technology, 2017, 31 (06): 33-40.
A.Kontostathis. Essential Dimensions of Latent Semantic Indexing (EDLSI) // In: Proceedings of the 40th Annual Hawaii International Conference on System Sciences. Kona Hawaii: IEEE CS Press, 2007. 73-80.
A.Atreya, C.Elkan. Latent Semantic Indexing (LSI) Fails for TREC collections. SIGKDD Explorations, 2011, 12(2): 5-10.
M.M. Hossain, V.Prybutok, N.Evangelopoulos. Causal Latent Semantic Analysis (cLSA): An Illustration. International Business Research, 2011, 4(2): 38-50
M.S.Zhang, Research on Joint Analysis Model of Chinese Lexical, Syntactic and Semantic. Harbin Institute of Technology, 2014.
J.Xu, J.H. Li, Q.M.Zhu,et al. Chinese semantic role annotation based on phrases and dependent syntactic structures. Computer Engineering, 2011, 37 (24): 169-172.
J.S. Ren, Z.Y.Wang, A New Language Model for Latent Semantic Analysis. High Technology Communications, 2005, 15 (8): 1-5.