Korean Anaphora Recognition System to Develop Healthcare Dialogue-Type Agent
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity. Methods: Anaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system. Results: The precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method. Conclusions: The hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.
Abstract
Objectives: Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity. Methods: Anaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system. Results: The precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method. Conclusions: The hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.
참고문헌 (26)
- Peral J, "Translation of pronominal anaphora between English and Spanish: Discrepancies and evaluation", J Artif Intell Res, 18, pp.117~147 (2003)
- Zhou X, "Approaches to text mining for clinical medical records", Proceedings of the 2006 ACM Symposium on Applied Computing, pp.235~239 (2006)
- 송미화, "A Multi-Classifier Based Guideline Sentence Classification System", Healthcare Informatics Research, 17(4), pp.224~231 (2011), 대한의료정보학회
- Chakrabarti S, "Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies", VLDB J, 7(3), pp.163~178 (1998)
- Chang JT, "Creating an online dictionary of abbreviations from MEDLINE", J Am Med Inform Assoc, 9(6), pp.612~620 (2002)
- Hsu WH, "Activities of the KSU Bioinformatics and Medical Informatics (BMI) Working Group, 2001-2002", pp.2002
- Wycoff DA, "Distributed laboratory computing:integration of a laboratory computer into a hospital information system", Am J Clin Pathol, 70(3), pp.390~399 (1978)
- Burke MD, "Clinical laboratory consultation: appropriateness to laboratory medicine", Clin Chim Acta, 333(2), pp.125~129 (2003)
- Kratz A, "The generation of narrative interpretations in laboratory medicine: a description of service-specific sign-out rounds", Am J Clin Pathol, 116(Suppl), pp.S133~S140 (2001)
- Lim EM, "Quality assessment of interpretative commenting in clinical chemistry", Clin Chem, 50(3), pp.632~637 (2004)
- Kratz A, "Enhanced clinical consulting:moving toward the core competencies of laboratory professionals", Clin Chim Acta, 319(2), pp.117~125 (2002)
- Hripcsak G, "Unlocking clinical data from narrative reports: a study of natural language processing", Ann Intern Med, 122(9), pp.681~688 (1995)
- 이수경, "Predictors of Medication Adherence in Elderly Patients with Chronic Diseases Using Support Vector Machine Models", Healthcare Informatics Research, 19(1), pp.33~41 (2013), 대한의료정보학회[DOI]
- Sujin Kim, "A Comparison of Intensive Care Unit Mortality Prediction Models through the Use of Data Mining Techniques", Healthcare Informatics Research, 17(4), pp.232~243 (2011), 대한의료정보학회
- Wang S, "Shape deformation: SVM regression and application to medical image segmentation", Proceedings of the 8th IEEE International Conference on Computer Vision, pp.209~216 (2001)
- Do TN, "Incremental SVM and visualization tools for bio-medical data mining", Proceedings of the European Workshop on Data Mining and Text Mining for Bioinformatics, pp.14~19 (2003)
- Li S, "A SVM-based framework for autonomous volumetric medical image segmentation using hierarchical and coupled level sets", Int Congr Ser, 1268, pp.207~212 (2004)
- Amaral IF, "Hierarchical medical image annotation using SVM-based approaches", Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine, pp.1~5 (2010)
- Evans R, "Applying machine learning toward an automatic classification of it", Lit Linguist Comput, 16(1), pp.45~57 (2001)
- Mojsilovic A, "Semantic based categorization, browsing and retrieval in medical image databases", Proceedings of the 2002 International Conference on Image Processing, pp.145~148 (2002)
- Lee Y, "Compositional knowledge management for medical services on semantic web", Proceedings of the 13th international World Wide Web Conference on Alternate Track Papers & Posters, pp.498~499 (2004)
- Cimino JJ, "Auditing the Unified Medical Language System with semantic methods", J Am Med Inform Assoc, 5(1), pp.41~51 (1998)
- 윤지현, "Development of Clinical Contents Model Markup Language for Electronic Health Records", Healthcare Informatics Research, 18(3), pp.171~177 (2012), 대한의료정보학회
- 황경훈, "Medical Image Retrieval: Past and Present", Healthcare Informatics Research, 18(1), pp.3~9 (2012), 대한의료정보학회
- Arch-int N, "Semantic ontology mapping for interoperability of learning resource systems using a rule-based reasoning approach", Expert Syst Appl, 40(18), pp.7428~7443 (2003)
- Choi S, "Semantic conceptenriched dependence model for medical information retrieval", J Biomed Inform, 47, pp.18~27 (2014)