Abstract
Semantic annotation of discourse is always one of most important tasks in natural language processing (NLP). We proposed a complex semantic representation mechanism for Chinese complex sentences. The semantic relations between sentences and between words can be represented as a semantic dependency graph by recursive directed graph. We studied the basic definition, the types of relations, and dependency direction of semantic dependence, and discussed the formal representation mechanism of semantic dependency from phrase-level, sentence-level and discourse-level. The semantic dependency graph model is characterized by allowing multiple correlations, allowing recursion and nesting, and formal representations are shown in recursive directed graph. The semantic dependency graph can more comprehensively represent the semantic relations between words and between the clauses in the discourse.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, B., Ji, D.H., Chen, L.: Semantic labeling of Chinese subject-predicate predicate sentence based on feature structure. J. Chin. Inf. Process. 26(3), 22–26 (2012). (in Chinese)
Chen, B., Ji, D.H., Chen, L.: Semantic labeling of Chinese serial-verbs sentence based on feature structure. J. Chin. Inf. Process. 27(5), 60–66 (2013). (in Chinese)
Chen, B., Lyu, C., Wei, X., Ji, D.: Semantic labeling of Chinese verb-complement structure based on feature structure. In: Su, X., He, T. (eds.) CLSW 2014. LNCS (LNAI), vol. 8922, pp. 341–348. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-14331-6_34
Zwicky, A.M.: Heads. J. Linguist. 21(1), 1–29 (1985)
Eisner, J., Smith, N.A.: Parsing with soft and hard constraints on dependency length. In: International Workshop on Parsing Technology, pp. 30–41. Association for Computational Linguistics (2005)
Mel’cuk, I.: Dependency Syntax: Theory and Practice. State University of New York Press, Albany (1988)
Feng, W.H.: The Dependency-Based Analysis of Chinese Conjunctions and the Related Constructions. Wuhan University (2011). (in Chinese)
Qiu, L.K., Jin, P., Wang, H.F.: A multi-view Chinese treebank based on dependency grammar. J. Chin. Inf. Process. 29(3), 9–15 (2005). (in Chinese)
Prasad, R., et al.: The penn discourse TreeBank 2.0. In: International Conference on Language Resources and Evaluation, LREC 2008, 26 May–1 June 2008, Marrakech, DBLP, pp. 2961–2968 (2008)
Xue, N.: Annotating discourse connectives in the Chinese Treebank. In: The Workshop on Frontiers in Corpus Annotations II: Pie in the Sky, pp. 84–91. Association for Computational Linguistics (2005)
Zhang, W.X., Qiu, L.K.: Study on connectives collocation based on corpus. Chin. Teach. World 82(4), 64–74 (2007). (in Chinese)
Chen, B., Lyu, C., Wei, X.M., Ji, D.H.: Chinese semantic parsing based on feature structure with recursive directed graph. Wuhan Univ. J. Nat. Sci. 20(4), 318–322 (2015)
Chen, B.: Building a Chinese Semantic Resource Based on Feature Structure. Wuhan University Press (2014). (in Chinese)
Acknowledgment
The work is funded by the following projects: National Natural Science Foundation of China No. 61772378, 61702121, Humanities & Social Science Foundation of Ministry of Education of China No. 16YJCZH004, and Science & Technology Project of Guangzhou No. 201704030002.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, B., Lyu, C., Ji, Z. (2018). Study on Chinese Discourse Semantic Annotation Based on Semantic Dependency Graph. In: Hong, JF., Su, Q., Wu, JS. (eds) Chinese Lexical Semantics. CLSW 2018. Lecture Notes in Computer Science(), vol 11173. Springer, Cham. https://doi.org/10.1007/978-3-030-04015-4_64
Download citation
DOI: https://doi.org/10.1007/978-3-030-04015-4_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04014-7
Online ISBN: 978-3-030-04015-4
eBook Packages: Computer ScienceComputer Science (R0)