arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1811.00436cs.CL
收藏

基于伪反馈蒸馏的无监督双级联学习在基于查询的抽取摘要中的应用

Unsupervised Dual-Cascade Learning with Pseudo-Feedback Distillation for Query-based Extractive Summarization

IBM Research(IBM研究院)

Haggai Roitman, Guy Feigenblat, David Konopnicki, Doron Cohen, Odellia Boni

摘要:

我们提出了Dual-CES -一种新的无监督,以查询为中心,多文档提取摘要。Dual-CES旨在更好地处理摘要中显着性和焦点之间的权衡。为此,Dual-CES采用两步双级联优化方法和基于显着性的伪反馈蒸馏。总的来说,Dual-CES的性能明显优于所有其他最先进的无监督替代品。Dual-CES甚至被证明能够胜过强监督摘要器。

英文摘要:

We propose Dual-CES -- a novel unsupervised, query-focused, multi-document extractive summarizer. Dual-CES is designed to better handle the tradeoff between saliency and focus in summarization. To this end, Dual-CES employs a two-step dual-cascade optimization approach with saliency-based pseudo-feedback distillation. Overall, Dual-CES significantly outperforms all other state-of-the-art unsupervised alternatives. Dual-CES is even shown to be able to outperform strong supervised summarizers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑