Grant: Discovery Grants Program - Individual
University of Western Ontario
$31,000.00
Argumentation in scholarly biomedical research papers
EF 2013-14
Résumé
Society's need for biomedical knowledge grows and grows. The repository for this knowledge, the scholarly biomedical literature, is thus growing at an ever increasing rate. In 2005, there were more than 16 million publications in MEDLINE, the online biomedical literature service, and more than 1800 publications were being added every day. No unaided human can keep pace with this rate of knowledge accumulation. The development of computer aids is therefore necessary.Computers are very good at searching such large amounts of information. However, the common keyword search methods typically return too much information. The search needs to be properly focussed. To do this we are suggesting the use of citations in the research articles to provide paths through the literature. But, unfortunately, searching only with the citation links still explodes exponentially. To overcome this drawback, we suggest a further refinement to the citation links: label the link with the citation role, for example, does the citation refer to a paper that it supports or contradicts, or does the citation refer to a paper that has an experimental procedure of note.To label the citations with their roles requires automatic techniques because of the vast amount of literature. We have begun to build software tools to accomplish this process. Our research has indicated that to have methods sophisticated enough to determine citation roles at a low error rate we need to understand the structure of the author's argument in the paper. This research proposal sets out a plan to accomplish this. In addition to citation role labelling, having the argument structure in a single paper has given us an exciting future research direction: assembling larger arguments across multiple papers from the arguments that exist in each paper.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
36853-2010
Name nom
Mercer, Robert
Department département
Computer Science
Organization id
36
Institution établissement
University of Western Ontario
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2010
Award amount
31000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
4
Nb partie
5
Application title
Argumentation in scholarly biomedical research papers
Keyword
NSERC
Application summary
Society's need for biomedical knowledge grows and grows. The repository for this knowledge, the scholarly biomedical literature, is thus growing at an ever increasing rate. In 2005, there were more than 16 million publications in MEDLINE, the online biomedical literature service, and more than 1800 publications were being added every day. No unaided human can keep pace with this rate of knowledge accumulation. The development of computer aids is therefore necessary.Computers are very good at searching such large amounts of information. However, the common keyword search methods typically return too much information. The search needs to be properly focussed. To do this we are suggesting the use of citations in the research articles to provide paths through the literature. But, unfortunately, searching only with the citation links still explodes exponentially. To overcome this drawback, we suggest a further refinement to the citation links: label the link with the citation role, for example, does the citation refer to a paper that it supports or contradicts, or does the citation refer to a paper that has an experimental procedure of note.To label the citations with their roles requires automatic techniques because of the vast amount of literature. We have begun to build software tools to accomplish this process. Our research has indicated that to have methods sophisticated enough to determine citation roles at a low error rate we need to understand the structure of the author's argument in the paper. This research proposal sets out a plan to accomplish this. In addition to citation role labelling, having the argument structure in a single paper has given us an exciting future research direction: assembling larger arguments across multiple papers from the arguments that exist in each paper.