论文标题
潜在提示调整文本摘要
Latent Prompt Tuning for Text Summarization
论文作者
论文摘要
具有不同控制信号的提示（例如，长度，关键字等）可用于控制文本摘要。当可用的控制信号可用时，它们可以控制生成的摘要的属性并有可能提高摘要质量（因为提供了更多信息）。不幸的是，在推理时间内尚未提供控制信号。在本文中，我们提出了Lotus（用于摘要的潜在提示调整的速记），这是一个单个模型，可以在受控和不受控制的（无控制信号）模式中应用。在培训期间，Lotus使用对比度学习目标从带有黄金控制信号的提示中学习潜在的及时表示。实验表明，在四个不同的摘要数据集中，在强（无法控制的）摘要模型上，莲花在不受控制的模式下始终如一地改善。我们还证明，可以使用用户指定的控件令牌的提示来控制生成的摘要。
Prompts with different control signals (e.g., length, keywords, etc.) can be used to control text summarization. When control signals are available, they can control the properties of generated summaries and potentially improve summarization quality (since more information are given). Unfortunately, control signals are not already available during inference time. In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes. During training, Lotus learns latent prompt representations from prompts with gold control signals using a contrastive learning objective. Experiments show Lotus in uncontrolled mode consistently improves upon strong (uncontrollable) summarization models across four different summarization datasets. We also demonstrate generated summaries can be controlled using prompts with user specified control tokens.
