26 research outputs found
Extraction of explanation based symptom-treatment relation from texts
No full textThis paper aims to extract the explanation-based
Problem-Solving relation, especially the Symptom-Treatment
relation, from hospital-web-board documents. The extracted
relations benefit people who are learning how to solve their
health problems. The research includes three main problems: 1)
how to identify symptom-concept EDUs (where an EDU is an
elementary discourse unit or a simple sentence/clause) and
treatment concept EDUs, 2) how to identify the symptomconcept-EDU
boundary and the treatment-concept-EDU
boundary as an explanation, 3) how to determine SymptomTreatment
relations from documents. Therefore, we propose
collecting each Multi-Word-Co occurrence with either a
symptom concept or a treatment concept from a verb-phrase to
identify each symptom-concept EDU and each treatment-concept
EDU including their boundaries. Collecting Multi-Word-Co
involves two more problems of the ambiguous Multi-Word-Co
and the Multi-Word-Co size. Thus, we apply the Bayesian
Network to solve both problems of Multi-Word-Co after applying
word rules. The Symptom-Treatment relation can be solved by
Naive Bayes learning vector pairs of symptom vectors and
treatment vectors. The research results can provide high
precision when extracting Symptom-Treatment relations through
texts
Construction of Disease-Symptom Knowledge Graph from Web-Board Documents
No full textThe research aim is to construct a disease-symptom knowledge graph (DSKG) as a cause-effect knowledge graph containing disease-symptom relations as a cause-effect relation type determined from downloaded documents on medical web-board resources. Each disease-symptom relation connects a disease-name concept node (a causative-concept node) to a corresponding node having a group of correlated symptom-concept/effect-concept features as common symptom-concept/effect-concept features among some disease-name concepts. The DSKG benefits non-professionals in preliminary diagnosis through a recommender web-board. There are three main problems: how to determine symptom concepts from sentences without annotation on the documents having disease-name concepts as the documents’ topic-names; how to determine the disease-symptom relations from the documents with/without complications; and how to construct the DSKG involving high dimensional symptom-concept features after union of the correlated symptom-concept groups. Therefore, we apply a word co-occurrence pattern including medical-symptom expressions from Wikipedia including MeSH and the Lexitron Dictionary to determine the symptom concepts. The Cartesian product is applied for automatic-supervised machine learning to determine the disease-symptom relation. We propose using Principal Component Analysis for constructing the DSKG by dimensionality reduction in the symptom-concept features with minimized information loss. In contrast to previous works, the proposed approach enables the DSKG construction with precise and concise representation scores of 7.8 and 9, respectively
Herbal Medicinal-Property Knowledge Extraction from Text for Knowledge Base Construction
No full textExtraction of cause-effect-concept pair series from web documents
Get PDFThis research aims to extract a cause-effect-concept pair series of consequent event occurrences in health information of hospital web-boards. The extracted cause-effect-concept pair series representing a disease causation pathway benefits for the automatic diagnosis and solving system. Where each causative/effect event concept is expressed by an elementary discourse unit (EDU which is a simple sentence). The research has three problems; how to determine causative/effect concept EDUs from the documents containing some EDU occurrences with both causative concepts and effect concepts, how to determine the cause-effect relation between two adjacent EDUs having the discourse cue ambiguity, and how to extract cause-effect-concept pair series mingled with either a stimulation relation EDU or other non-cause-effect relation EDUs from the documents. Therefore, we apply annotated NWordCo pairs with causative-effect concepts to represent EDU pairs with causative-effect concept where the NWordCo size solved by Naïve Bayes. We also apply Naïve Bayes to solve NWordCo-concept pairs having the cause-effect relation from the adjacent EDU pairs. We then propose using cue words and the collected NWordCoconcept pairs with the cause-effect relation to extract the cause-effectconcept pair series. The research results provide the high precision of the cause-effect-concept pair series determination from the documents
Comparative Study of Using Word Co-occurrence to Extract Disease Symptoms from Web Documents
No full textEvent-Concept Pair Series Extraction to Represent Medical Complications from Texts
Get PDFThis 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
