A Hybrid Human-Computer Approach to the Extraction of Scientific Facts from the Literature

Published

June 28, 2016

Author(s)

Roselyne B. Tchoua, Kyle Chard, Debra Audus, Jian Qin, Juan J. de Pablo, Ian Foster

Abstract

A wealth of valuable data is locked within the millions of research articles published each year. Reading and extracting pertinent information from those articles has become an unmanageable task for scientists. This problem hinders scientific progress by making it hard to build on results buried in literature. Moreover, these data are loosely structured, encoded in manuscripts of various formats, embedded in different content types, and are, in general, not machine accessible. We present a hybrid human-computer solution for semi-automatically extracting scientific facts from literature. This solution combines an automated discovery, download, and extraction phase with a semi-expert crowd assembled from students to extract specific scientific facts. To evaluate our approach we apply it to a particularly challenging molecular engineering scenario, extraction of a polymer property: the Flory-Huggins interaction parameter. We demonstrate useful contributions to a comprehensive database of polymer properties.

Proceedings Title

Procedia Computer Science

Volume

80

Conference Dates

June 6-8, 2016

Conference Location

San Diego, CA, US

Conference Title

International Conference on Computational Science

Pub Type

Conferences

Download Paper

https://doi.org/10.1016/j.procs.2016.05.338

Local Download

Keywords

Crowdsourcing, Information Extraction, Classification, Flory-Huggins, Materials Science

Citation

Tchoua, R. , Chard, K. , Audus, D. , Qin, J. , de Pablo, J. and Foster, I. (2016), A Hybrid Human-Computer Approach to the Extraction of Scientific Facts from the Literature, Procedia Computer Science, San Diego, CA, US, [online], https://doi.org/10.1016/j.procs.2016.05.338, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=920680 (Accessed November 20, 2024)