Cargando…
Quantifying the advantage of domain-specific pre-training on named entity recognition tasks in materials science
A bottleneck in efficiently connecting new materials discoveries to established literature has arisen due to an increase in publications. This problem may be addressed by using named entity recognition (NER) to extract structured summary-level data from unstructured materials science text. We compar...
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Elsevier
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9024010/ https://www.ncbi.nlm.nih.gov/pubmed/35465225 http://dx.doi.org/10.1016/j.patter.2022.100488 |