方法证据记录
Weakly supervised text summarization
Weakly supervised text summarization trains abstractive or extractive summarization models without manually annotated reference summaries. Instead of costly human labels, it exploits weak signals — heuristic rules, distant supervision, noisy automatic labels, or self-supervised objectives — to guide sequence-to-sequence or transformer models toward producing coherent, concise summaries of input documents.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Weakly Supervised Text Summarization
分类方法记录 · ml-model / deep-learning
- 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. · URL
- 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. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。