Sofia J Athenikos1, Hyoil Han. 1. College of Information Science and Technology, Drexel University, Philadelphia, PA 19104, USA. sofia.j.athenikos@acm.org
Abstract
OBJECTIVES: In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions for the future research development in this critical area of intersection between Artificial Intelligence, Information Retrieval, and Biomedical Informatics. MATERIALS AND METHODS: We devised a conceptual framework within which to categorize current QA approaches. In particular, we used "semantic knowledge-based QA" as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed techniques in the QA process, and we further classified those approaches into three subcategories: (1) semantics-based, (2) inference-based, and (3) logic-based. Based on the framework, we first conducted a survey of open-domain or non-biomedical-domain QA approaches that belong to each of the three subcategories. We then conducted an in-depth review of biomedical QA, by first noting the characteristics of, and resources available for, biomedical QA and then reviewing medical QA approaches and biological QA approaches, in turn. The research articles reviewed in this paper were found and selected through online searches. RESULTS: Our review suggested the following tasks ahead for the future research development in this area: (1) Construction of domain-specific typology and taxonomy of questions (biological QA), (2) Development of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4) More extensive and integrated utilization of semantic knowledge throughout the QA process, and (5) Incorporation of logic and reasoning mechanisms for answer inference. CONCLUSION: Corresponding to the growth of biomedical information, there is a growing need for QA systems that can help users better utilize the ever-accumulating information. Continued research toward development of more sophisticated techniques for processing NL text, for utilizing semantic knowledge, and for incorporating logic and reasoning mechanisms, will lead to more useful QA systems. Copyright 2009 Elsevier Ireland Ltd. All rights reserved.
OBJECTIVES: In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions for the future research development in this critical area of intersection between Artificial Intelligence, Information Retrieval, and Biomedical Informatics. MATERIALS AND METHODS: We devised a conceptual framework within which to categorize current QA approaches. In particular, we used "semantic knowledge-based QA" as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed techniques in the QA process, and we further classified those approaches into three subcategories: (1) semantics-based, (2) inference-based, and (3) logic-based. Based on the framework, we first conducted a survey of open-domain or non-biomedical-domain QA approaches that belong to each of the three subcategories. We then conducted an in-depth review of biomedical QA, by first noting the characteristics of, and resources available for, biomedical QA and then reviewing medical QA approaches and biological QA approaches, in turn. The research articles reviewed in this paper were found and selected through online searches. RESULTS: Our review suggested the following tasks ahead for the future research development in this area: (1) Construction of domain-specific typology and taxonomy of questions (biological QA), (2) Development of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4) More extensive and integrated utilization of semantic knowledge throughout the QA process, and (5) Incorporation of logic and reasoning mechanisms for answer inference. CONCLUSION: Corresponding to the growth of biomedical information, there is a growing need for QA systems that can help users better utilize the ever-accumulating information. Continued research toward development of more sophisticated techniques for processing NL text, for utilizing semantic knowledge, and for incorporating logic and reasoning mechanisms, will lead to more useful QA systems. Copyright 2009 Elsevier Ireland Ltd. All rights reserved.
Authors: Brian L Cairns; Rodney D Nielsen; James J Masanz; James H Martin; Martha S Palmer; Wayne H Ward; Guergana K Savova Journal: AMIA Annu Symp Proc Date: 2011-10-22
Authors: Parikshit Sondhi; Jimeng Sun; ChengXiang Zhai; Robert Sorrentino; Martin S Kohn Journal: J Am Med Inform Assoc Date: 2012-03-21 Impact factor: 4.497
Authors: Chaitanya Shivade; Courtney Hebert; Marcelo Lopetegui; Marie-Catherine de Marneffe; Eric Fosler-Lussier; Albert M Lai Journal: J Biomed Inform Date: 2015-09-14 Impact factor: 6.317
Authors: Emilie Pasche; Patrick Ruch; Douglas Teodoro; Angela Huttner; Stephan Harbarth; Julien Gobeill; Rolf Wipfli; Christian Lovis Journal: PLoS One Date: 2013-04-30 Impact factor: 3.240