ScholarGate
Msaidizi
Machine learningDeep learning / NLP / CV

Utambuzi wa Huluki Zilizotajwa Unaoelezeka

Utambuzi wa Huluki Zilizotajwa Unaoelezeka (XAI-NER) huunganisha modeli ya kawaida ya NER — kwa kawaida kiweka lebo cha mfuatano cha BERT-based au BiLSTM-CRF — na mbinu za kuelezewa za baada ya tukio au za ndani kama vile LIME, SHAP, uonyeshaji wa umakini, au saliency inayotegemea gradient ili kufichua ni kwa nini kila tokeni ilipewa lebo maalum ya huluki. Uwazi huu ni muhimu katika nyanja zenye hatari kubwa kama vile maandishi ya kliniki, nyaraka za kisheria, na fasihi ya kibiolojia.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

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

Vyanzo

  1. 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
  2. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why Should I Trust You?": Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. DOI: 10.1145/2939672.2939778

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Explainable Named Entity Recognition (XAI-NER). ScholarGate. https://scholargate.app/sw/deep-learning/explainable-named-entity-recognition

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

Imerejelewa na

ScholarGateExplainable Named Entity Recognition (Explainable Named Entity Recognition (XAI-NER)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/explainable-named-entity-recognition · Seti ya data: https://doi.org/10.5281/zenodo.20539026