论文标题
COLO：基于对比度学习的重新排列框架，用于一阶段摘要
COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization
论文作者
论文摘要
用于提取性和抽象性摘要系统的传统培训范例始终仅使用令牌级别或句子级培训目标。但是，始终从摘要级别评估输出摘要，从而导致培训和评估的不一致。在本文中，我们提出了一个基于对比度学习的重新排列框架，用于一阶段的摘要，称为COLO。通过建模对比度目标，我们表明摘要模型能够根据摘要级别的分数直接生成摘要，而无需其他模块和参数。广泛的实验表明，Colo在CNN/DailyMail基准测试中提高了单阶段系统的提取和抽象结果，在44.58和46.33 Rouge-1得分中得分，同时保留了参数效率和推理效率。与最先进的多阶段系统相比，我们节省了100多个GPU培训时间，并在推断期间获得3〜8加速比，同时保持可比的结果。
Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives. However, the output summary is always evaluated from summary-level which leads to the inconsistency in training and evaluation. In this paper, we propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. By modeling a contrastive objective, we show that the summarization model is able to directly generate summaries according to the summary-level score without additional modules and parameters. Extensive experiments demonstrate that COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score while preserving the parameter efficiency and inference efficiency. Compared with state-of-the-art multi-stage systems, we save more than 100 GPU training hours and obtaining 3~8 speed-up ratio during inference while maintaining comparable results.
