東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Algorithms for Relation Extraction f...

State University of New York at Buffalo., Computer Science and Engineering.

FindBook

Google Book

Amazon

博客來

Algorithms for Relation Extraction from Biomedical Texts.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Algorithms for Relation Extraction from Biomedical Texts./
作者:	Liu, Sijia.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	126 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-09, Section: B.
Contained By:	Dissertations Abstracts International80-09B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13425440
ISBN:	9780438944770

Algorithms for Relation Extraction from Biomedical Texts.
Liu, Sijia.

Algorithms for Relation Extraction from Biomedical Texts. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 126 p.

Source: Dissertations Abstracts International, Volume: 80-09, Section: B.

Thesis (Ph.D.)--State University of New York at Buffalo, 2019.

This item must not be added to any third party search indexes.

The boost in the capacity and volume of biomedical texts, including biomedical literatures and electronic health records (EHRs), has created a tremendous opportunity for biomedical research and practice. It is widely acknowledged that relation extraction of unstructured textual contents using natural language processing (NLP) and text mining techniques is essential for using biomedical data for secondary purposes, which leads to the increasing demands on NLP systems and approaches. Relation extraction is defined as the task to resolve the relations among the mentioned entities in the textual context. The diversity and complexity of semantic relations from biomedical texts make it challenging for a unified solution to different tasks. This motivates us to strive towards the development of diverse approaches, including distant supervised, rule-based and deep learning methods, to resolve biomedical relation extraction problems. Towards this end, the dissertation consists of proposed solutions to several relation extraction tasks in biomedical domain: 1) Coreference Resolution: we proposed an infinite mixture model to resolve coreferent relations among mentions in clinical notes. A similarity measure function is proposed to determine the coreferent relations. 2) Drug-Drug Interaction: we proposed a relation classification framework based on topic modeling augmented with distant supervision for the task of DDI from biomedical text. Our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications comparing with other approaches. 3) Event Time Association of Lab Test Results: we proposed a rule-based relation extraction system to extract the relations between lab test results and temporal information from clinical texts. 4) Chemical Protein Relation: we proposed an attention-based neural networks method to extract interaction information between chemical, genes and proteins (ChemProt). The attention weight distribution and top attention words show that the attention mechanism is effective in highlighting semantic association and textual variants of ChemProt relations without prior domain knowledge and extensive feature engineering.

ISBN: 9780438944770Subjects--Topical Terms:

523869
Computer science.

Algorithms for Relation Extraction from Biomedical Texts.
LDR:03360nmm a2200325 4500 001 2262970
005 20191121113951.5
008 220629s2019 ||||||||||||||||| ||eng d
020 $a 9780438944770
035 $a (MiAaPQ)AAI13425440
035 $a (MiAaPQ)buffalo:16175
035 $a AAI13425440
040 $a MiAaPQ $c MiAaPQ
100 1 $a Liu, Sijia. $3 3540044
245 1 0 $a Algorithms for Relation Extraction from Biomedical Texts.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 126 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-09, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Chaudhary, Vipin.
502 $a Thesis (Ph.D.)--State University of New York at Buffalo, 2019.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a The boost in the capacity and volume of biomedical texts, including biomedical literatures and electronic health records (EHRs), has created a tremendous opportunity for biomedical research and practice. It is widely acknowledged that relation extraction of unstructured textual contents using natural language processing (NLP) and text mining techniques is essential for using biomedical data for secondary purposes, which leads to the increasing demands on NLP systems and approaches. Relation extraction is defined as the task to resolve the relations among the mentioned entities in the textual context. The diversity and complexity of semantic relations from biomedical texts make it challenging for a unified solution to different tasks. This motivates us to strive towards the development of diverse approaches, including distant supervised, rule-based and deep learning methods, to resolve biomedical relation extraction problems. Towards this end, the dissertation consists of proposed solutions to several relation extraction tasks in biomedical domain: 1) Coreference Resolution: we proposed an infinite mixture model to resolve coreferent relations among mentions in clinical notes. A similarity measure function is proposed to determine the coreferent relations. 2) Drug-Drug Interaction: we proposed a relation classification framework based on topic modeling augmented with distant supervision for the task of DDI from biomedical text. Our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications comparing with other approaches. 3) Event Time Association of Lab Test Results: we proposed a rule-based relation extraction system to extract the relations between lab test results and temporal information from clinical texts. 4) Chemical Protein Relation: we proposed an attention-based neural networks method to extract interaction information between chemical, genes and proteins (ChemProt). The attention weight distribution and top attention words show that the attention mechanism is effective in highlighting semantic association and textual variants of ChemProt relations without prior domain knowledge and extensive feature engineering.
590 $a School code: 0656.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a State University of New York at Buffalo. $b Computer Science and Engineering. $3 1035503
773 0 $t Dissertations Abstracts International $g 80-09B.
790 $a 0656
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13425440