聯合詞性與局部語境於中文健康照護實體關係擷取;Joint Part-of-Speech and Local Context for Chinese Healthcare Entity-Relationship Extraction

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/90058

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/90058

Title:	聯合詞性與局部語境於中文健康照護實體關係擷取;Joint Part-of-Speech and Local Context for Chinese Healthcare Entity-Relationship Extraction
Authors:	盧建寰;Lu, Chien-Huan
Contributors:	電機工程學系
Keywords:	轉譯器;開放式資訊擷取;知識圖譜;健康資訊學;Transformers;Open Information Extraction;Knowledge Graph;Health Informatics
Date:	2022-08-25
Issue Date:	2022-10-04 12:09:45 (UTC+8)
Publisher:	國立中央大學
Abstract:	開放式資訊擷取對於資訊理解甚是重要，此任務可以有效將複雜語句的文本簡單化，利用大量三元組形式來表達文本的重點信息，而所謂的三元組即是 (實體 1，關係，實體 2) ，利用這個形式來更加淺顯易懂的表達語句中潛在的關係。因此我們提出一個管道式模型 CHERE (Chinese Healthcare Entity-Relationship Extraction)，此模型將實體擷取模型和關係擷取模型分開訓練，再結合在一起使用。整體模型為利用 ME-MGNN 擷取出實體對，並採用基於轉換器 RoBERTa 自然語言預訓練模型的關係模型，從文本中擷取該實體對淺在的關係，進而形成三元組。由於現階段中文領域的開放式資訊擷取資料集相當缺乏，更遑論健康照護領域，因此我們人工標記一組語料庫，資料來源主要來自維基百科，總共有 5,879 個句子，包含 22,944 個實體以及 8,879 個三元組。其中此語料庫每句話都至少具有兩個以上的實體標記，部分資料具有三元組。最後透過實驗，我們得到 CHERE 在不同 F1-Score 評估指標下得到 0.6966 (Exact Match) 、0.7795 (Contain Match) 和 0.7986 (Token-Level Match) 等效能，其分數皆優異於其他開放式擷取模型 SpanOIE、Mulit2OIE、CHOIE。;Open Information Extraction (OpenIE) is used to effectively simplify complex sentences in the form of triples such as (entity 1, relation, relation 2), which is an important technique to extract potential knowledge embedded in the sentences for natural language understanding. In this study, we propose a pipelined architecture, called CHERE (Chinese Healthcare Entity- Relationship Extraction), including an entity recognition model and a relationship extraction model. The ME-MGNN neural network is used to recognize entities, and their combined entity pairs are fed into the RoBERTa transformer for potential relation extraction. We manually annotate collected datasets for Chinese healthcare entity-relationship extraction because of a lack of publicly available benchmark data. The collected data mainly came from Wikipedia. In summary, our constructed data includes 5,879 sentences with a total of 22,944 entities and 8,879 triples. Each sentence contains at least two entities, where some entities contains the entity- relationship triples. Experimental results show our proposed CHERE model achieved the exact match F1 of 0.6966, contain match F1 of 0.7795, and token-level match F1 of 0.7986, which outperforms than compared models including SpanOIE, Multi2OIE, and CHOIE.
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	36	View/Open

社群 sharing

Loading...