ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Selgitatavad lausengebedid

Selgitatavad lausengebedid ühendavad tihedate lauserepresentatsioonide õppimise post-hoc või intrinise interpretatsioonivahenditega – nagu uurimisklassifikaatorid, LIME, SHAP või tähelepanu atribuutika – et paljastada, millist lingvistilist ja semantilist teavet sisaldab laus vektor ja miks alluv mudel teeb antud ennustuse. Eesmärk on säilitada kaasaegsete kodeerijate representatsioonivõime, muutes nende käitumise auditeeritavaks.

Ava rakenduses MethodMindPeagiVideoPeagiDownload slides

Loe meetodi täielikku kirjeldust

Ainult liikmetele

Selle osa lugemiseks logi sisse tasuta kontoga.

Logi sisse

Method map

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

Allikad

  1. Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018). What you can cram into a single $\vec{v}$ector: Probing sentence embeddings for linguistic properties. In Proceedings of ACL 2018, pp. 2126–2136. link
  2. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why Should I Trust You?": Explaining the predictions of any classifier. In Proceedings of KDD 2016, pp. 1135–1144. DOI: 10.1145/2939672.2939778

Kuidas sellele lehele viidata

ScholarGate. (2026, June 3). Explainable Sentence Embeddings (Interpretable Dense Sentence Representations). ScholarGate. https://scholargate.app/et/deep-learning/explainable-sentence-embeddings

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 Sentence Embeddings (Explainable Sentence Embeddings (Interpretable Dense Sentence Representations)). Loetud 2026-06-15 aadressilt https://scholargate.app/et/deep-learning/explainable-sentence-embeddings · Andmestik: https://doi.org/10.5281/zenodo.20539026