SEMANTIC ROLE MARKING FOR CLINICAL TEXT IN KAZAKH

Semantic role labeling (SLR) extracts a superficial representation of meanings and their relationships from various texts, the semantic layer is important for understanding natural language. Few studies in the labeling of semantic roles have been conducted in the field of medicine, mainly due to the lack of annotated clinical buildings, especially in Russian. The aim of this work is to develop a framework for marking semantic roles for clinical notes using the corps created by practicing clinicians to increase productivity and save costs, as well as improve the quality of predictive medicine. Materials and methods: an anonymous database, collected on the basis of clinical practice, in particular, diseases of the gastrointestinal tract, cardiovascular system and others, was used as a data set of the target domain. Records were manually analyzed and tagged. The framework of semantic markup is presented and the analysis of the applicability of semantic roles and their relationships with respect to real clinical cases is given.

1. Pradhan S. S., Ward W. H., Hacioglu K., et al. Shallow semantic parsing using support vector machines / In: Proceedings of Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics. - Boston, Massachusetts, USA: Association for Computational Linguistics July 21-26, 2004. - P. 233-240.

2. Allen J. Natural Language Understanding. / 2nd ed. Menlo Park, CA: Benjamin / Cummings., 1995.

3. Surdeanu M., Harabagiu S., Williams J., et al. Using predicate-argument structures for information extraction // In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics. Sapporo, Japan: Association for Computational Linguistics July 7-12, 2003. - P. 8-15.

4. Akane Y., Yusuke M., Tomoko O., et al. Automatic construction of predicate- argument structure patterns for biomedical information extraction. In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. Seattle, Washington, USA: Association for Computational Linguistics July 22-23, 2006. - P. 284-292.

5. Yakushiji A., Miyao Y., Tateisi Y., et al. Biomedical information extraction with predicate-argument structure patterns. In: Proceedings of the First International Symposium on Semantic Mining in Biomedicine. Hinxton, Cambridge, UK: European Bioinformatics Institute April 10-13, 2005. - P. 60-69.

6. Nguyen N. T. H., Miwa M., Tsuruoka Y., et al. Open information extraction from biomedical literature using predicate-argument structure patterns // In: Proceedings of the 5th International Symposium on Languages in Biology and Medicine. Zurich, Switzerland December 12-13, 2013.

7. Wattarujeekrit T., Shah P. K., Collier N. PASBio: predicate-argument structures for event extraction in molecular biology. BMC Bioinformatics 200. - P. 155.

8. Kogan Y., Collier N., Pakhomov S., et al. Towards semantic role labeling & IE in the medical literature. AMIA Symposium October 22-26, 2005.-P. 410-414.

9. Shah P. K., Bork P. LSAT: learning about alternative transcripts in MEDLINE. Bioinformatics 2006. - P. 857-865.

10. Bethard S., Lu Z., Martin J. H., et al. Semantic role labeling for protein transport predicates. BMC Bioinformatics 2008. - P. 277.

11. Barnickel T., Weston J., Collobert R., et al. Large scale application of neural network based semantic role labeling for automated relation extraction from biomedical texts. PloS One 2009. - P. e6393.

12. Paek H., Kogan Y., Thomas P., et al. Shallow semantic parsing of randomized controlled trial reports. AMIA Symposium November 11-15, 2006. - P. 604-608.

13. Albright D., Lanfranchi A., Fredriksen A., et al. Towards comprehensive syntactic and semantic annotations of the clinical narrative. J Am Med Inform Assoc. 2013. - P. 922-930.

14. Wang Y., Pakhomov S., Melton G. B. Predicate argument structure frames for modeling information in operative notes. Stud Health Technol Inform. 2013. - P. 783-787.

15. Meyers A., Reeves R., Macleod C., et al. Annotating noun argument structure for NomBank. In: Proceedings of the Language Resources and Evaluation Conference. Lisbon, Portugal: European Language Resources Association May 26-28, 2004. - P. 803-806.

16. Meyers A., Reeves R., Macleod C., et al. The NomBank Project: an interim peport. In: Proceedings of the HLT-NAACL 2004 Workshop: Frontiers in Corpus Annotation. Boston, Massachusetts, USA: Association for Computational Linguistics May 6, 2004. - P. 24-31

17. Palmer M., Gildea D., Kingsbury P. The proposition bank: an annotated corpus of semantic roles. Comput Linguist. 2005. - P. 71-106.

18. Rindflesch T. C., Fiszman M. The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text. J Biomed Inform. 2003. - P. 462-477.

19. Kilicoglu H., Shin D., Fiszman M., et al. SemMedDB: a PubMed-scale repository of biomedical semantic predications. Bioinformatics 2012. - P. 3158-3160.

20. Sager N. Natural Language Information Processing. UK; Addison-Wesley,1981.

21. Chen E. S., Hripcsak G., Xu H., et al. Automated acquisition of disease-drug knowledge from biomedical and clinical documents: an initial study. Jam Med Inform Assoc. 2008. - P. 87-98.

22. Simpson M. S., Demner-Fushman D. Biomedical text mining: a survey of recent progress. In: Aggarwal C. C., Zhai C., eds. Mining Text Data. USA; Springer 2012. - P. 465-517.

23. Schuler K. K. VerbNet: A Broad-Coverage, Comprehensive Verb Lexicon. ProQuest Paper AAI3179808, 2005.

24. Ruppenhofer J., Ellsworth M., Petruck M. R. L., et al. FrameNet II: extended the ory and practice. http://framenet.icsi.berkeley.edu/ Accessed 10 March 2014.

25. Levin B. English Verb Classes and Alternations: a Preliminary Investigation. - Chicago, USA: University of Chicago Press 1993.