Ontology-Based Computing of Sentence Similarity

  • Zixian ZhangEmail author
  • Xuning Liu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)


Sentence similarity is the basis for many natural language processing tasks and it is studied in this paper by the tools of ontology and Wikipedia-based Wiktionary. If a word appears in the definition of another word in Wiktionary, the two words can be said to be related to each other. Based on this kind of knowledge from Wiktionary, a graph-based ontology is built. In the graph, nodes represent words, and if one word appears in the definition of the other, there is a line between them in the graph. And the line or degree as it is called is used to compute word similarity. Accordingly, word similarity is used to compute sentence similarity. In the paper, content words such as nouns, verbs, adjectives and adverbs are used to computer sentence similarity. Sentence similarity computed in this way is effective for natural language processing tasks such as question answering, information extraction, etc. And it is used in online chat robot “FreeTalker”.


Natural language processing Sentence similarity Ontology Wiktionary 


  1. 1.
    Bruening, B.: Ditransitive asymmetries and a theory of idiom formation. Linguist. Inq. 41(4), 519–562 (2010)CrossRefGoogle Scholar
  2. 2.
    Hatzivassiloglou, V., McKeown, K.R.: Predicting the semantic orientation of adjectives. In Proceedings of the Eighth Conference on European Chapter of the Association for Computational Linguistics, pp. 174–181 (1997)Google Scholar
  3. 3.
    Adamic, L.A., Adar, E.: Friends and neighbors on the web. Soc. Netw. 25(3), 211–230 (2003)CrossRefGoogle Scholar
  4. 4.
    Dumais, S.T.: Latent semantic analysis. Ann. Rev. Inf. Sci. Technol. 38(1), 188–230 (2004)CrossRefGoogle Scholar
  5. 5.
    Newman, M.E.J.: Clustering and preferential attachment in growing networks. Phys. Rev. E 64(2), 025102 (2001)CrossRefGoogle Scholar
  6. 6.
    Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. ISDN Syst. 30(1–7), 107–117 (1998)CrossRefGoogle Scholar
  7. 7.
    Lin, H., Bilmes, J.: How to select a good training-data subset for transcription: submodular active selection for sequences. In Proceedings of Conference of the International Speech Communication Association (2009)Google Scholar
  8. 8.
    Lin, H., Bilmes, J.: Multi-document summarization via budgeted maximization of submodular functions. In: Proceedings of NAACL-HLT (2010)Google Scholar
  9. 9.
    Zhao, J., Lan, M., Niu, Z., Lu, Y.: Integrating word embeddings and traditional NLP features to measure textual entailment and semantic relatedness of sentence pairs. In: The International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, 12–17 July, pp. 1–7 (2015)Google Scholar
  10. 10.
    Han, X., Mao, X.: Improved algorithm of word semantic similarity. China Sciencepaper 11(2), 202–207 (2016)Google Scholar
  11. 11.
    Lyu, C., Lu, Y., Ji, D., Chen, B.: Deep learning for textual entailment recognition. In: 27th International Conference on Tools with Artificial Intelligence, pp. 154–161 (2015)Google Scholar
  12. 12.
    Wu, Y., Li, S., Liu, J., Guo, L., Wu, X.: NETASPNO: approximate strict pattern matching under nonoverlapping condition. IEEE Access 6(1), 24350–24361 (2018)CrossRefGoogle Scholar
  13. 13.
    Wu, Y., Shen, C., Jiang, H., Wu, X.: Strict pattern matching under non-overlapping condition. Sci. China Inf. Sci. 60(1), 012–101 (2017)CrossRefGoogle Scholar
  14. 14.
    Wu, Y., Tang, Z., Jiang, H., Wu, X.: Approximate pattern matching with gap constraints. J. Inf. Sci. 42(5), 639–658 (2016)CrossRefGoogle Scholar
  15. 15.
    Wu, Y., Fu, S., Jiang, H., Wu, X.: Strict approximate pattern matching with general gaps. Appl. Intell. 42(3), 566–580 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Liaocheng UniversityLiaochengChina
  2. 2.China University of Mining and TechnologyBeijingChina
  3. 3.Shijiazhuang UniversityShijiazhuangChina

Personalised recommendations