Extracting and modeling geographic information from scientific articles

Abstract

Scientific articles often contain relevant geographic information such as where field work was performed or where patients were treated. Most often, this information appears in the full-text article contents as a description in natural language including place names, with no accompanying machine-readable geographic metadata. Automatically extracting this geographic information could help conduct meta-analyses, find geographical research gaps, and retrieve articles using spatial search criteria. Research on this problem is still in its infancy, with many works manually processing corpora for locations and few cross-domain studies. In this paper, we develop a fully automatic pipeline to extract and represent relevant locations from scientific articles, applying it to two varied corpora. We obtain good performance, with full pipeline precision of 0.84 for an environmental corpus, and 0.78 for a biomedical corpus. Our results can be visualized as simple global maps, allowing human annotators to both explore corpus patterns in space and triage results for downstream analysis. Future work should not only focus on improving individual pipeline components, but also be informed by user needs derived from the potential spatial analysis and exploration of such corpora.

An Approach Based on Open Research Knowledge Graph for Knowledge Acquisition from Scientific Papers

“…The contributions created using the template were used to build a comparison table 7 . The latter compares papers related to the "epidemiological surveillance system design and implementation" research problem.…”

“…This wealth of scientific knowledge is widely disseminated to users who now possess an unprecedented problem of access to scientific literature [4,5,6]. In effect, this increase in scientific content poses significant challenges for the researchers who want to sort through, read, understand, compare, and build upon to determine for instance, the state of art in their respective field of interest [4,7].…”

“…After its acquisition, knowledge is organized in such a way that it can be used and reused whenever needed. Globally, knowledge acquisition can happen through a wide variety of strategies that vary from completely manual to totally automated [1,7,8]. Concerning knowledge acquisition from scientific papers, we distinguished the manual process [1,7,10,11] and the (semi-)automatic process.…”

Digital Document Analysis Using Weighted Score Convolutional Neural Network and Arc Factored Graph Based Dependency Parsing

“…Also by separating functional processing and structural processing, precision and recall could be improved. Parsing for obtaining geographic information has been presented in [14]. This technique employs fully automatic pipe line model.…”