The Construction and Annotation of a Semantically Enriched Database: The Mandarin VerbNet and Its NLP Applications

  • Meichun LiuEmail author
Part of the Frontiers in Chinese Linguistics book series (FiCL, volume 9)


Linguistic analysis has been questioned of its applicational value. However, with the proper framework, linguistic wisdom may be needed in the last mile of big data era. This paper introduces a lexical semantic database, Mandarin VerbNet, which is built from a frame-based constructional approach, as a linguistically motivated, computationally feasible, and Chinese-appropriate resource. The study also tests the validity of adopting the semantically-enriched and constructionally-cued features for the task of Word Sense Disambiguation. Four Chinese polysemous verbs of emotion are chosen for a pilot trial. With the annotation of frame-specific features, the different senses can be detected with a high performance rate. The results consistently show significant improvement for all the disambiguation tasks over the baselines, with the weight average F∆max. up to 0.337. The impressive results indicate the discriminative effect of frame-based constructional information, and ultimately points to the potential advantage of employing deep linguistic annotation in NLP applications.


Mandarin VerbNet Lexical semantics Frame-based constructional approach Word sense disambiguation Linguistic annotation 









Degree marker












  1. Boas, H.C. 2003. Towards a lexical-constructional account of the locative alternation. In Proceedings of the 2001 Western conference, 27–42.Google Scholar
  2. Chan, Y.S., T.N. Hwee, and C. David. 2007. Word sense disambiguation improves statistical machine translation. Annual Meeting-Association for Computational Linguistics 45(1).Google Scholar
  3. Chen, K.J. et al. 1999. The CKIP Chinese Treebank: guidelines for annotation. In ATALA workshop IV Treebanks, 85–96, Paris.Google Scholar
  4. Fillmore, C.J. 1982. Frame semantics. In Linguistic society of Korea, linguistics in the morning Calm, 111–137, Seoul: Hanshin Publishing Co.Google Scholar
  5. Fillmore, C.J., and F.C. Baker. 2000. FrameNet: Frame semantics meets the corpus. In Proceedings of the 74th annual meeting of the linguistic society of America.Google Scholar
  6. Goldberg, A.E. 1995. Constructions: A construction grammar approach to argument structure. Chicago: University of Chicago Press.Google Scholar
  7. Iwata, S. 2004. Over-prefixation: A lexical constructional approach. English Language and Linguistics 8 (2): 239–292.CrossRefGoogle Scholar
  8. Iwata, S. 2005. Locative alternation and two levels of verb meaning. Cognitive Linguistics 16 (2): 355–408.CrossRefGoogle Scholar
  9. Kaplan, A. 1955. An experimental study of ambiguity and context. Mechanical Translation 2 (2): 39–46.Google Scholar
  10. Lesk, M. 1986. Automated sense disambiguation using machine-readable dictionaries: How to tell a pine cone from an ice cream cone. In Proceedings of the 1986 ACM SIGDOC conference, 24–26, Toronto, Canada.Google Scholar
  11. Levin, B. 1993. English verb classes and alternations: A preliminary investigation. University of Chicago Press.Google Scholar
  12. Li, C.N., and S.A. Thompson. 1976. Subject and topic: A new typology of language. In Li, C.N. (ed.). Subject and topic. New York: Academic Press.Google Scholar
  13. Li, C.N., and S.A. Thompson. 1981. Mandarin Chinese: A functional reference grammar. Berkeley: University of California Press.Google Scholar
  14. Liu, M., Y.-W. Chen, and C.-Y. Hu. 2013. Semantic prominence in the interpretation of locative role: the case of chu-lai/chu-qu. In Paper presented at the 21th annual meeting of the international association of Chinese linguistics. National Taiwan Normal University.Google Scholar
  15. Liu, M., and J.C. Chang. 2015. Redefining locative inversion in mandarin: A lexical-constructional approach. In Tao, H. (ed.). Proceeding of the 27th North American conference on Chinese linguistics (NACCL-27) UCLA, 439–461.Google Scholar
  16. Liu, M. 2016. Emotion in Lexicon and Grammar: Lexical-constructional interface of mandarin emotional predicates. Lingua Sinica 2 (1): 4.CrossRefGoogle Scholar
  17. Liu, M., and J. Chang. 2019. From caused motion to spatial configuration: Placement verbs in Mandarin. Language and Linguistics 20 (2): 180–224.CrossRefGoogle Scholar
  18. Manning, C.D., and H. Schütze, 1999. Foundations of statistical natural language processing. MIT Press.Google Scholar
  19. Marcus, G. 2018. Deep learning: A critical appraisal. arXiv:1801.00631.
  20. Mihalcea, R., and P. Edmonds. 2004. Proceedings of senseval-3: Third International wok shop on the evaluation of systems for the semantic analysis of text. Barcelona, Spain.Google Scholar
  21. Navigli, R. 2009. Word sense disambiguation: A survey. ACM Computing Surveys 41 (2): 10.CrossRefGoogle Scholar
  22. Qian, Y., and S. Piao. 2009. The development of a semantic annotation scheme for Chinese kinship. Corpora 4 (2): 189–208.CrossRefGoogle Scholar
  23. Schuler, K.K. 2005. VerbNet: A broad-coverage, comprehensive verb lexicon.Google Scholar
  24. Wilks, et al. 1990. Providing machine tractable dictionary tools. In Pustejovsky, J. (ed.). Semantics and the lexicon, 341–401 Dordrecht, Kluwer Academic Publishers.Google Scholar
  25. Xue, N., and M. Palmer. 2005. Automatic semantic role labeling for Chinese verbs. In Proceedings of the 19th international joint conference on artificial intelligence, 1160–1165, Edinburgh, Scotland.Google Scholar
  26. You, L., and K. Liu. 2005. Building Chinese FrameNet database. In Paper presented at natural language processing and knowledge engineering.Google Scholar

Website Resources

  1. Sinica Chinese Treebank.
  2. The Proposition Bank (PropBank).

Copyright information

© Peking University Press 2020

Authors and Affiliations

  1. 1.Department of Linguistics and TranslationCity University of Hong KongHong KongChina

Personalised recommendations