Ensemble automated approaches for producing high‐quality herbarium digital records
Abstract Premise One of the slowest steps in digitizing natural history collections is converting labels associated with specimens into a digital data record usable for collections management and research. Here, we address how herbarium specimen labels can be converted into digital data records via...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Applications in Plant Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aps3.11623 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542913446281216 |
|---|---|
| author | Robert P. Guralnick Raphael LaFrance Julie M. Allen Michael W. Denslow |
| author_facet | Robert P. Guralnick Raphael LaFrance Julie M. Allen Michael W. Denslow |
| author_sort | Robert P. Guralnick |
| collection | DOAJ |
| description | Abstract Premise One of the slowest steps in digitizing natural history collections is converting labels associated with specimens into a digital data record usable for collections management and research. Here, we address how herbarium specimen labels can be converted into digital data records via extraction into standardized Darwin Core fields. Methods We first showcase the development of a rule‐based approach and compare outcomes with a large language model–based approach, in particular ChatGPT4. We next quantified omission and commission error rates across target fields for a set of labels transcribed using optical character recognition (OCR) for both approaches. For example, we find that ChatGPT4 often creates field names that are not Darwin Core compliant while rule‐based approaches often have high commission error rates. Results Our results suggest that these approaches each have different strengths and limitations. We therefore developed an ensemble approach that leverages the strengths of each individual method and documented that ensembling strongly reduced overall information extraction errors. Discussion This work shows that an ensemble approach has particular value for creating high‐quality digital data records, even for complicated label content. While human validation is still needed to ensure the best possible quality, automated approaches can speed digitization of herbarium specimen labels and are likely to be broadly usable for all natural history collection types. |
| format | Article |
| id | doaj-art-b44163dd367e4e2d86d99e70a1411f8c |
| institution | Kabale University |
| issn | 2168-0450 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applications in Plant Sciences |
| spelling | doaj-art-b44163dd367e4e2d86d99e70a1411f8c2025-02-03T12:21:34ZengWileyApplications in Plant Sciences2168-04502025-01-01131n/an/a10.1002/aps3.11623Ensemble automated approaches for producing high‐quality herbarium digital recordsRobert P. Guralnick0Raphael LaFrance1Julie M. Allen2Michael W. Denslow3Florida Museum of Natural History University of Florida Gainesville Florida USAFlorida Museum of Natural History University of Florida Gainesville Florida USADepartment of Biological Sciences VirginiaTech Blacksburg Virginia USAFlorida Museum of Natural History University of Florida Gainesville Florida USAAbstract Premise One of the slowest steps in digitizing natural history collections is converting labels associated with specimens into a digital data record usable for collections management and research. Here, we address how herbarium specimen labels can be converted into digital data records via extraction into standardized Darwin Core fields. Methods We first showcase the development of a rule‐based approach and compare outcomes with a large language model–based approach, in particular ChatGPT4. We next quantified omission and commission error rates across target fields for a set of labels transcribed using optical character recognition (OCR) for both approaches. For example, we find that ChatGPT4 often creates field names that are not Darwin Core compliant while rule‐based approaches often have high commission error rates. Results Our results suggest that these approaches each have different strengths and limitations. We therefore developed an ensemble approach that leverages the strengths of each individual method and documented that ensembling strongly reduced overall information extraction errors. Discussion This work shows that an ensemble approach has particular value for creating high‐quality digital data records, even for complicated label content. While human validation is still needed to ensure the best possible quality, automated approaches can speed digitization of herbarium specimen labels and are likely to be broadly usable for all natural history collection types.https://doi.org/10.1002/aps3.11623ChatGPTdigitizationensemble methodsinformation extractionlarge language modelsmachine learning |
| spellingShingle | Robert P. Guralnick Raphael LaFrance Julie M. Allen Michael W. Denslow Ensemble automated approaches for producing high‐quality herbarium digital records Applications in Plant Sciences ChatGPT digitization ensemble methods information extraction large language models machine learning |
| title | Ensemble automated approaches for producing high‐quality herbarium digital records |
| title_full | Ensemble automated approaches for producing high‐quality herbarium digital records |
| title_fullStr | Ensemble automated approaches for producing high‐quality herbarium digital records |
| title_full_unstemmed | Ensemble automated approaches for producing high‐quality herbarium digital records |
| title_short | Ensemble automated approaches for producing high‐quality herbarium digital records |
| title_sort | ensemble automated approaches for producing high quality herbarium digital records |
| topic | ChatGPT digitization ensemble methods information extraction large language models machine learning |
| url | https://doi.org/10.1002/aps3.11623 |
| work_keys_str_mv | AT robertpguralnick ensembleautomatedapproachesforproducinghighqualityherbariumdigitalrecords AT raphaellafrance ensembleautomatedapproachesforproducinghighqualityherbariumdigitalrecords AT juliemallen ensembleautomatedapproachesforproducinghighqualityherbariumdigitalrecords AT michaelwdenslow ensembleautomatedapproachesforproducinghighqualityherbariumdigitalrecords |