ScholarGate
Asistents

Salīdzināt metodes

Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.

Entitāšu izsekošana starp dokumentiem×Informācijas ieguve×
NozareTeksta ieguveTeksta ieguve
SaimeProcess / pipelineProcess / pipeline
Izcelsmes gads1998 (scoring foundations); 2019 (neural joint model)
Autors
TipsNLP pipeline — cross-document coreference resolutionNLP structured-information task
PirmavotsBagga, A. & Baldwin, B. (1998). Algorithms for Scoring Coreference Chains. In Proceedings of the LREC 1998 Linguistic Coreference Workshop, pp. 563–566. link ↗Cowie, J. & Lehnert, W. (1996). Information Extraction. Communications of the ACM. DOI ↗
Citi nosaukumicross-document coreference resolution, cross-doc entity linking, Belge Ötesi Varlık TakibiIE, structured information extraction, Bilgi Çıkarma (Information Extraction)
Saistītās44
KopsavilkumsCross-document entity tracking, formally known as cross-document coreference resolution, identifies and merges all references to the same real-world entity scattered across a collection of documents. Rooted in the B3 evaluation framework introduced by Bagga and Baldwin (1998) and substantially advanced by the neural joint model of Barhom et al. (2019), the method builds entity clusters that span document boundaries — enabling multi-document understanding, knowledge-base population, and corpus-wide entity analysis.Information extraction (IE) is a natural-language-processing task that converts unstructured text into structured information — such as events, relations, and attributes — so that facts buried in free-form documents become machine-readable records. The task was consolidated in early surveys by Cowie and Lehnert (1996) and later by Grishman (2012).
ScholarGateDatu kopa
  1. v1
  2. 2 Avoti
  3. PUBLISHED
  1. v1
  2. 2 Avoti
  3. PUBLISHED

Doties uz meklēšanu Lejupielādēt slaidus

ScholarGateSalīdzināt metodes: Cross-Document Entity Tracking · Information Extraction. Izgūts 2026-06-17 no https://scholargate.app/lv/compare