如何利用弱监督训练文本摘要模型
How to Train Text Summarization Model with Weak Supervisions
AI总结：
本文提出一种将复杂目标分解为简单子任务并生成弱监督信号的方法，实现无标签端到端训练主题摘要模型，在CNN和DailyMail数据集上取得优异效果。
摘要：
当前，机器学习技术在各类应用中取得了显著成功。这些技术大多依赖人工生成的标签，或来自多个来源的噪声与不精确标签的混合监督。然而，对于某些复杂任务，由于目标本身的复杂性，即使噪声或不精确的标签也难以获得。为解决这一问题，我们提出一种方法，将复杂目标分解为更简单的子任务，并为每个子任务生成监督信号。随后，我们将这些监督信号整合为一种易于处理的形式，从而形成一个直接的学习流程。作为案例研究，我们展示了一个用于基于主题的摘要系统。该系统利用丰富的监督信号同时提升摘要质量和主题相关性。值得注意的是，我们能够在没有任何标签的情况下端到端地训练模型。实验结果表明，我们的方法在CNN和DailyMail数据集上表现非常出色。
英文摘要：
Currently, machine learning techniques have seen significant success across various applications. Most of these techniques rely on supervision from human-generated labels or a mixture of noisy and imprecise labels from multiple sources. However, for certain complex tasks, even noisy or inexact labels are unavailable due to the intricacy of the objectives. To tackle this issue, we propose a method that breaks down the complex objective into simpler tasks and generates supervision signals for each one. We then integrate these supervision signals into a manageable form, resulting in a straightforward learning procedure. As a case study, we demonstrate a system used for topic-based summarization. This system leverages rich supervision signals to promote both summarization and topic relevance. Remarkably, we can train the model end-to-end without any labels. Experimental results indicate that our approach performs exceptionally well on the CNN and DailyMail datasets.
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。
