用简单任务生成监督信号，无标签也能训练摘要模型。
How to Train Text Summarization Model with Weak Supervisions
- 将复杂摘要目标拆解为多个简单任务，自动生成监督信号
- 在CNN和DailyMail数据集上实现优异性能，无需任何人工标注
- 适合缺乏标注数据的摘要任务，尤其适用于主题相关摘要
目前机器学习技术在诸多应用中取得显著成功，大多依赖人类标注或来自多个来源的噪声标签。然而，对于某些复杂任务，由于目标本身的复杂性，甚至噪声标签也难以获得。为此，我们提出一种方法：将复杂目标分解为若干简单任务，为每个任务生成监督信号，并将其整合为可管理的形式，从而实现简洁的学习流程。以主题型摘要为例，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。令人瞩目的是，模型可在无任何标签的情况下端到端训练。实验结果表明，该方法在CNN和DailyMail数据集上表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。