Abstract
Many aspects of macroevolutionary theory and our understanding of biotic responses to global environmental change derive from literature-based compilations of paleontological data. Existing manually assembled databases are, however, incomplete and difficult to assess and enhance with new data types. Here, we develop and validate the quality of a machine reading system, PaleoDeepDive, that automatically locates and extracts data from heterogeneous text, tables, and figures in publications. PaleoDeepDive performs comparably to humans in several complex data extraction and inference tasks and generates congruent synthetic results that describe the geological history of taxonomic diversity and genus-level rates of origination and extinction. Unlike traditional databases, PaleoDeepDive produces a probabilistic database that systematically improves as information is added. We show that the system can readily accommodate sophisticated data types, such as morphological data in biological illustrations and associated textual descriptions. Our machine reading approach to scientific data integration and synthesis brings within reach many questions that are currently underdetermined and does so in ways that may stimulate entirely new modes of inquiry.
Highlights
Paleontology is based on the description and classification of fossils, an enterprise that has played out in an untold number of scientific publications
We have demonstrated that our machine reading system is capable of building a structured database from the heterogeneous scientific literature with quality that is comparable to a database produced by humans manually reading and extracting data
We have tested at a large scale the reproducibility of the Paleobiology Database (PBDB), and in so doing we have identified sources of error and inconsistency that have a bearing on the use of Taxonomic group All genera Bivalvia Bryozoa Gastropoda Anthozoa Brachiopoda Reptilia Trilobita Cephalopoda Mammalia Crinoidea
Summary
Paleontology is based on the description and classification of fossils, an enterprise that has played out in an untold number of scientific publications. Founded nearly two decades ago by a small team who generated the first sampling-standardized global Phanerozoic taxonomic diversity curves [12,13], the PBDB has since grown to include an international group of more than 380 scientists with diverse research agendas. This group has spent approximately nine continuous person years entering over 300,000 taxonomic names, 530,000 opinions on the status and classification of those names, and 1.2 million fossil occurrences (i.e., temporally and geographically resolved instances of fossils). Because the end product of manual data entry is a list of facts that are divorced from most, if not all, original contexts, assessing the quality of the database and the reproducibility of results is difficult
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
