Problem Content Table Construction Based on Extracting Sym-Multi-Word-Co from Texts

  • Chaveevan PechsiriEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 807)


This research aims to construct a problem content table, particularly health-problem/symptom contents from downloaded health-care documents. The content table includes Disease Name, Symptom Concept, Symptom-Location Concept, and Sym-Multi-Word-Co Expression (which is a multi-word co-occurrence having a symptom concept on verb phrases). The research results benefit for a diagnosis system. The research has four problems; how to identify Sym-Multi-Word-Co from verb phrases, how to determine Sym-Multi-Word-Co boundaries after stemming words and eliminating stop words, how to solve Sym-Multi-Word-Co ambiguities, and how to derive symptom concepts and location concepts from Sym-Multi-Word-Co expressions with implicit-symptom-location occurrences. Therefore, we apply the symptom-verb-concept set to identify Sym-Multi-Word-Co and also to solve the Sym-Multi-Word-Co ambiguities. We also propose Bayesian Network to solve the Sym-Multi-Word-Co boundaries. We apply WordNet and MeSH to derive symptom concepts and implicit-symptom-location concepts. The research results provide the symptom content table with the high precision of the Sym-Multi-Word-Co extraction from the documents.


Multi-word co-occurrence Verb phrase Symptom content 



This work has been supported by the Department of Information Technology, Dhurakij Pundit University, Thailand. Moreover, Onuma Moolwat, Achara, and Uraiwan Janviriyasopak have contributed greatly in this research.


  1. 1.
    Carlson, L., Marcu, D., Okurowski, M.E.: Building a discourse-tagged corpus in the framework of rhetorical structure theory. In: Current Directions in Discourse and Dialogue, pp. 85–112 (2003)Google Scholar
  2. 2.
    Miller, G.: WordNet: a lexical database. Commun. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  3. 3.
    Fader, A., Soderland, S., Etzioni, O.: Identifying relations for open information extraction. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 1535–1425 (2011)Google Scholar
  4. 4.
    Ando, S., Fujii, Y., Ito, T.: Filtering harmful sentences based on multiple word co-occurrence. In: IEEE/ACIS 9th International Conference on Computer and Information Science (ICIS) (2010)Google Scholar
  5. 5.
    Riaz, M., Girju, R.: Recognizing causality in verb-noun pairs via noun and verb semantics. In: Proceedings of the EACL 2014 Workshop on Computational Approaches to Causality in Language, pp. 48–57 (2014)Google Scholar
  6. 6.
    Mitchell, T.M.: Machine Learning. The McGraw-Hill Companies Inc. and MIT Press, Singapore (1997)zbMATHGoogle Scholar
  7. 7.
    Sudprasert, S., Kawtrakul, A.: Thai word segmentation based on global and local unsupervised learning. In: NCSEC 2003 Proceeding (2003)Google Scholar
  8. 8.
    Chanlekha, H., Kawtrakul, A.: Thai named entity extraction by incorporating maximum entropy model with simple heuristic information. In: IJCNLP 2004 Proceedings (2004)Google Scholar
  9. 9.
    Chareonsuk, J., Sukvakree, T., Kawtrakul, A.: Elementary discourse unit segmentation for Thai using discourse cue and syntactic information. In: NCSEC 2005 Proceedings (2005)Google Scholar
  10. 10.
    Jensen, F.V.: Bayesian Networks and Decision Graphs. Springer, Secaucus (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Information TechnologyDhurakij Pundit UniversityBangkokThailand

Personalised recommendations