Event-Concept Pair Series Extraction to Represent Medical Complications from Texts
| Autor: | Chaveevan Pechsiri, Sumran Phainoun |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Control and Optimization
Relation (database) Computer Networks and Communications Computer science Verb 02 engineering and technology computer.software_genre Set (abstract data type) 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Event (probability theory) NWordCo business.industry Intersection (set theory) 020207 software engineering Verb phrase Unit Event-Concept Pair Series Elementary Discourse Hardware and Architecture Signal Processing 020201 artificial intelligence & image processing Artificial intelligence business Complication computer Sentence Natural language processing Information Systems |
| Zdroj: | Indonesian Journal of Electrical Engineering and Computer Science. 12:1320 |
| ISSN: | 2502-4760 2502-4752 |
| DOI: | 10.11591/ijeecs.v12.i3.pp1320-1333 |
| Popis: | This research aims to determine an event-concept pair series as consequent events, particularly a cause-effect-concept pair series on disease documents downloaded from hospital-web-boards. These series are used for representing medical/disease complications which benefit for solving system. Each causative/effect event concept is expressed by a verb phrase of an elementary discourse unit which is a simple sentence. The research had three problems; how to determine each adjacent-simple-sentence pair having the cause-effect relation, how to determine each cause-effect-concept pair series mingled with simple sentences having non-cause-effect-relations, and how to identify the complication of several extracted cause-effect-concept pair series from the documents. Therefore, we extract NWordCo-concept set having the causative/effect concepts from the sentences’ verb phrases including a support vector machine to solve each NWordCo size. We apply the Naive Bayes classifier to extract an NWordCo-concept pair set as a knowledge template having the cause-effect relation from the documents. We then propose using the knowledge template to extract several cause-effect-concept pair series. We also apply the intersection of the NWordCo-concept sets to identify the common-cause/effect for representing the complicationdevelopment parts of these extracted series. The research results provide a high percent correctness of the cause-effect-concept-pair series determination from the documents. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|