New publication: Backes, Iurshina, Shahid, Mayr: Comparing free reference extraction pipelines


Categories: GESIS-News

Backes, T., Iurshina, A., Shahid, M.A. et al. Comparing free reference extraction pipelines. Int J Digit Libr (2024). https://doi.org/10.1007/s00799-024-00404-6

In this paper, the authors compare the performance of several popular pre-trained reference extraction and segmentation toolkits combined in different pipeline configurations on three different datasets. The extraction is end-to-end, i.e. the input is PDF documents, and the output is parsed reference objects. The evaluation is for reference strings and individual fields in the reference objects using alignment by identical fields and close-to-identical values.

The results show that Grobid and AnyStyle perform best of all compared tools, although one may want to use them in combination. The work is meant to serve as a reference for researchers interested in applying out-of-the-box reference extraction and -parsing tools, for example, as a preprocessing step to a more complex research question.