ScholarGate
Asisten
Machine learningDeep learning / NLP / CV

Ringkasan Teks Berawasi Lemah

Ringkasan teks berawasi lemah melatih model ringkasan abstrak atau ekstraktif tanpa ringkasan referensi yang dianotasi secara manual. Alih-alih label manusia yang mahal, ia memanfaatkan sinyal lemah — aturan heuristik, pengawasan jarak jauh, label otomatis yang berisik, atau tujuan pengawasan mandiri — untuk memandu model urutan-ke-urutan atau transformer guna menghasilkan ringkasan dokumen masukan yang koheren dan ringkas.

Buka di MethodMindSegeraVideoSegeraDownload slides

Baca metode selengkapnya

Khusus anggota

Masuk dengan akun gratis untuk membaca bagian ini.

Masuk

Method map

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

Ringkasan Teks Berawasi Lemah
Pembelajaran Mandiri Ter…

Sumber

  1. 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
  2. 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

Cara menyitasi halaman ini

ScholarGate. (2026, June 3). Weakly Supervised Text Summarization. ScholarGate. https://scholargate.app/id/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.

Compare side by side
ScholarGateWeakly supervised text summarization (Weakly Supervised Text Summarization). Diakses 2026-06-15 dari https://scholargate.app/id/deep-learning/weakly-supervised-text-summarization · Set data: https://doi.org/10.5281/zenodo.20539026