Machine learningDeep learning / NLP / CV

Uundaji wa mada kwa njia ya kujifunza binafsi

Uundaji wa mada kwa njia ya kujifunza binafsi unachanganya ugunduzi wa mada unaoeleweka wa miundo ya mada ya kawaida na malengo ya kujifunza binafsi — kama vile hasara ya kulinganisha, uundaji wa lugha uliofunikwa, au urekebishaji — ili kujifunza mada zenye ushirikiano na utajiri wa maana kutoka kwa maandishi yasiyo na lebo bila lebo za binadamu. Inajenga daraja kati ya miundo ya mada ya kawaida ya uwezekano na ujifunzaji wa kisasa wa uwakilishi, ikitoa mada zinazolingana zaidi na maana ya muktadha.

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.

Uundaji wa mada kwa njia ya kujifunza binafsi

Uainishaji unaotumia BERT Mfumo wa Mada wa LDA Mfumo wa Mfumo wa Mada w…Uundaji wa mada unaosaid…Sentence Embeddings (Vib…

Vyanzo

Wu, X., Li, C., Zhu, Y., & Miao, Y. (2023). Effective Neural Topic Modeling with Embedding Clustering Regularization. Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202, 37335–37357. link ↗
Topic model. Wikipedia. link ↗

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Self-Supervised Topic Modeling. ScholarGate. https://scholargate.app/sw/deep-learning/self-supervised-topic-modeling

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.

Uainishaji unaotumia BERTUjifunzaji wa Kina↔ compare
Mfumo wa Mada wa LDAUjifunzaji wa Kina↔ compare
Mfumo wa Mfumo wa Mada wa NMFUjifunzaji wa Kina↔ compare
Uundaji wa mada unaosaidiwa na nusu (Semi-supervised Topic Modeling)Ujifunzaji wa Kina↔ compare
Sentence Embeddings (Vibandiko vya Sentensi)Ujifunzaji wa Kina↔ compare

Compare side by side →

Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →