Soalan-Jawapan Kendiri-Berpengawasan
Soalan-Jawapan Kendiri-Berpengawasan (SSQA) ialah paradigma latihan yang menjana pasangan soalan-jawapan secara automatik daripada teks tanpa label — menggunakan terjemahan cloze, penutupan rentang, atau penjanaan soalan neural — untuk melatih model QA tanpa sebarang data berlabel manusia. Ia membolehkan sistem pemahaman bacaan berkualiti tinggi walaupun set data anotasi jarang atau khusus domain.
Baca kaedah sepenuhnya
Log masuk dengan akaun percuma untuk membaca bahagian ini.
Method map
The neighbourhood of related methods — select a node to explore.
Sumber
- Lewis, P., Denoyer, L., & Riedel, S. (2019). Unsupervised Question Answering by Cloze Translation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 4896–4910. DOI: 10.18653/v1/P19-1484 ↗
- Alberti, C., Andor, D., Pitler, E., Devlin, J., & Collins, M. (2019). Synthetic QA Corpora Generation with Roundtrip Consistency. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 6168–6173. DOI: 10.18653/v1/p19-1620 ↗
Cara memetik halaman ini
ScholarGate. (2026, June 3). Self-supervised Question Answering (SSQA). ScholarGate. https://scholargate.app/ms/deep-learning/self-supervised-question-answering
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.
- Retrieval-Augmented Generation (RAG)Perlombongan Teks↔ compare
Dirujuk oleh
Terjumpa masalah pada halaman ini? Laporkan atau cadangkan pembetulan →