Svagt superviseret tekstresumé
Svagt superviseret tekstresumé træner abstrakte eller ekstraktive resumémodeller uden manuelt annoterede reference-resuméer. I stedet for dyre menneskelige labels udnytter det svage signaler – heuristiske regler, fjern-supervision, støjende automatiske labels eller selv-superviserede mål – til at guide sekvens-til-sekvens- eller transformer-modeller mod at producere sammenhængende, koncise resuméer af inputdokumenter.
Læs hele metoden
Log ind med en gratis konto for at læse dette afsnit.
Method map
The neighbourhood of related methods — select a node to explore.
Kilder
- Amplayo, R. K., & Lapata, M. (2020). Unsupervised Opinion Summarization with Noisy Autoencoder. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 1934–1945. link ↗
- Huang, L., Wu, L., & Wang, L. (2020). Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 5094–5107. link ↗
Sådan citerer du denne side
ScholarGate. (2026, June 3). Weakly Supervised Text Summarization. ScholarGate. https://scholargate.app/da/deep-learning/weakly-supervised-text-summarization
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.
- Selvovervåget læringMaskinlæring↔ compare
Har du fundet en fejl på denne side? Indberet den eller foreslå en rettelse →