DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Choi, Edward | - |
dc.contributor.advisor | 최윤재 | - |
dc.contributor.author | Kim, Daeyoung | - |
dc.date.accessioned | 2023-06-22T19:31:26Z | - |
dc.date.available | 2023-06-22T19:31:26Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032316&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308223 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.2,[iv, 20 p. :] | - |
dc.description.abstract | Question Answering on Electronic Health Records (EHR-QA) has a significant impact on the healthcare domain, and it is being actively studied. Previous research on structured EHR-QA focuses on converting natural language queries into query language such as SQL or SPARQL (NLQ2Query), so the problem scope is limited to pre-defined data types by the specific query language. In order to expand the EHR-QA task beyond this limitation to handle multi-modal medical data and solve complex inference in the future, more primitive systemic language is needed. In this paper, we design the program-based model (NLQ2Program) for EHR-QA as the first step towards the future direction. We tackle MIMICSPARQL*, the graph-based EHR-QA dataset, via a program-based approach in a semi-supervised manner in order to overcome the absence of gold programs. Without the gold program, our proposed model shows comparable performance to the previous state-of-the-art model, which is an NLQ2Query model (0.9% gain). In addition, for a reliable EHR-QA model, we apply the uncertainty decomposition method to measure the ambiguity in the input question. We empirically confirmed data uncertainty is most indicative of the ambiguity in the input question. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Question answering▼aUncertainty▼aElectronic health records | - |
dc.subject | 질의응답▼a불확실성▼a전자의무기록 | - |
dc.title | Uncertainty-aware text-to-program for question answering on structured electronic health records | - |
dc.title.alternative | 구조화된 전자의무기록에서 불확실성을 활용한 질의 응답 프로그램 생성 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 김대영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.