Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Reconnaissance d'entités nommées explicable× | Classification basée sur BERT× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2018–2020 | 2019 |
| Auteur d'origine≠ | Community-driven (NLP + XAI research) | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language) |
| Type≠ | Interpretability-augmented sequence labeling | Pre-trained language model with fine-tuning |
| Source fondatrice≠ | Danilevsky, M., Qian, K., Aharonov, R., Katsis, Y., Kawas, B., & Sen, P. (2020). A Survey of the State of Explainable AI for Natural Language Processing. Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL-IJCNLP), pp. 447–459. link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| Alias | XAI-NER, Interpretable NER, Transparent Named Entity Recognition, Explainable NER | BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS |
| Apparentées≠ | 6 | 4 |
| Résumé≠ | Explainable Named Entity Recognition (XAI-NER) combines a standard NER model — typically a BERT-based or BiLSTM-CRF sequence labeler — with post-hoc or intrinsic explainability techniques such as LIME, SHAP, attention visualization, or gradient-based saliency to reveal why each token was assigned a particular entity label. This transparency is essential in high-stakes domains like clinical text, legal documents, and biomedical literature. | BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data. |
| ScholarGateJeu de données ↗ |
|
|