ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Forklarlig RoBERTa-baseret klassifikation

Forklarlig RoBERTa-baseret klassifikation finjusterer en RoBERTa transformer-model på mærkede tekstdata og anvender derefter post-hoc fortolkelighedsmetoder — såsom SHAP, LIME eller attention-analyse — for at afsløre, hvilke tokens eller træk der drev hver forudsigelse. Dette bygger bro mellem state-of-the-art NLP-ydeevne og menneskeligt forståelig ræsonnement, hvilket opfylder både krav til nøjagtighed og gennemsigtighed.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692. link
  2. Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems (NeurIPS), 30, 4765–4774. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Explainable RoBERTa-based Text Classification with Post-hoc Interpretation. ScholarGate. https://scholargate.app/da/deep-learning/explainable-roberta-based-classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateExplainable RoBERTa-based Classification (Explainable RoBERTa-based Text Classification with Post-hoc Interpretation). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/explainable-roberta-based-classification · Datasæt: https://doi.org/10.5281/zenodo.20539026