Advertisement

Syntactic and Semantic Features Based Relation Extraction in Agriculture Domain

  • Zhanghui Liu
  • Yiyan Chen
  • Yuanfei Dai
  • Chenhao Guo
  • Zuwen Zhang
  • Xing ChenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)

Abstract

Relation extraction plays an important role in many natural language processing tasks, such as knowledge graph and question answering system. Up to the present, many of the former relation methods work directly on the raw word sequence, so it is often subject to a major limitation: the lack of semantic information, which leads to the problem of the wrong category. This paper presents a novel method to extract relation from Chinese agriculture text by incorporating syntactic parsing feature and word embedding feature. This paper uses word embedding to capture the semantic information of the word. On the basis of the traditional method, this paper integrates the dependency parsing, the core predicate and word embedding features, using the naive Bayes model, support vector machine (SVM) and decision tree to build experiment. We use the websites knowledge base to construct a dataset and evaluate our approach. Experimental results show that our proposed method achieves good performance on the agriculture dataset. The dataset and the word vectors trained by Word2Vec are available at Github (https://github.com/A-MuMu/agriculture.git).

Keywords

Relation extraction Word embedding Syntactic feature Semantic feature Agriculture field 

References

  1. 1.
    Wang, C.Y., Wang, F.: Study on recognition of Chinese agricultural named entity with conditional random fields. J. Agric. Univ. Hebei 37(1), 132–135 (2014)Google Scholar
  2. 2.
    Hu, D.P.: The research of question analysis based on ontology and architecture design for question answering system in agriculture. Ph.D. thesis, Chinese Academy of Agricultural Sciences (2013)Google Scholar
  3. 3.
    Chen, E., Qiu, S., Chang, X., Fei, T., Liu, T.: Word embedding:continuous space representation for natural language. J. Data Acquis. Process. 29(1), 19–29 (2014)Google Scholar
  4. 4.
    Kambhatla, N.: Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations. In: ACL 2004 on Interactive Poster and Demonstration Sessions, p. 22 (2013)Google Scholar
  5. 5.
    Jiang, J., Zhai, C.X.: A systematic exploration of the feature space for relation extraction. In: Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, 22–27 April 2007, Rochester, New York, USA, pp. 113120 (2007)Google Scholar
  6. 6.
    Li, H.G., Wu, X.D., Li, Z., Wu, G.G.: A relation extraction method of Chinese named entities based on location and semantic features. Appl. Intell. 38(1), 115 (2013)CrossRefGoogle Scholar
  7. 7.
    Guo, X., He, T., Hu, X.: Chinese named entity relation extraction based on syntactic and semantic features. J. Chin. Inf. Process 28(6), 183–189 (2014)Google Scholar
  8. 8.
    Chen, Y., Zheng, Q., Zhang, W.: Omni-word feature and soft constraint for Chinese relation extraction. In: Meeting of the Association for Computational Linguistics, pp. 572–581 (2014)Google Scholar
  9. 9.
    He, Y., Lyu, X., Xu, L.: Extraction of non-taxonomic relations between ontological concepts from Chinese patent documents. Comput. Eng. Des. 38(1), 97–102 (2017)Google Scholar
  10. 10.
    Zhang, Q., Guo, H., Zhang, Z.: Extracting entity relationship with word embedding representation features. Data Anal. Knowl. Discov. 1(9), 8–15 (2017)Google Scholar
  11. 11.
    Ma, X., Zhou, C., Lv, X.: Extraction of non-taxonomic relations based on SAO structure. Comput. Eng. Appl. 54(8), 220–225 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Zhanghui Liu
    • 1
    • 2
  • Yiyan Chen
    • 1
    • 2
  • Yuanfei Dai
    • 1
    • 2
  • Chenhao Guo
    • 1
    • 2
  • Zuwen Zhang
    • 1
    • 2
  • Xing Chen
    • 1
    • 2
    Email author
  1. 1.College of Mathematics and Computer ScienceFuzhou UniversityFuzhouChina
  2. 2.Key Laboratory of Network Computing and Intelligent Information ProcessingFuzhou UniversityFuzhouChina

Personalised recommendations