Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Extrakce strukturovaného textu× | Rozpoznávání pojmenovaných entit (NER)× | |
|---|---|---|
| Obor | Dolování textu | Dolování textu |
| Rodina | Process / pipeline | Process / pipeline |
| Rok vzniku | — | — |
| Tvůrce | — | — |
| Typ≠ | Document-processing pipeline | NLP sequence-labelling task |
| Původní zdroj≠ | Zhu, J. et al. (2021). TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content. ACL. link ↗ | Nadeau, D. & Sekine, S. (2007). A survey of named entity recognition. Lingvisticae Investigationes. link ↗ |
| Další názvy≠ | form extraction, table extraction, document parsing, Yapılandırılmış Veri Çıkarma (Form & Tablo Çıkarma) | NER, entity tagging, Adlandırılmış Varlık Tanıma (NER) |
| Příbuzné≠ | 2 | 3 |
| Shrnutí≠ | Structured text extraction is a document-processing pipeline that automatically identifies and pulls tables, form fields, and structured data from PDF, HTML, and scanned documents. It converts heterogeneous document layouts into machine-readable, analysis-ready records and is widely used in data collection workflows, document digitisation projects, and academic corpus construction. | Named entity recognition (NER) is a natural-language-processing task that automatically detects and labels entities in text — such as people, organisations, locations, and dates. Surveyed by Nadeau and Sekine (2007) and later advanced with neural architectures by Lample et al. (2016), it turns free-running text into tagged spans that downstream tools can use. |
| ScholarGateDatová sada ↗ |
|
|