论文标题
Brio：将秩序提出抽象性摘要
BRIO: Bringing Order to Abstractive Summarization
论文作者
论文摘要
抽象性摘要模型通常使用最大似然估计进行训练，该估计假设确定性（单点）目标分布，其中理想模型将将所有概率质量分配给参考摘要。此假设可能导致推理期间的性能降解，在这种推论中，模型需要比较几个系统生成的（候选）摘要，这些摘要偏离了参考摘要。为了解决这个问题，我们提出了一个新颖的培训范式，该范围假设非确定性分布，以便根据其质量分配不同的候选摘要。我们的方法在CNN/Dailymail（47.78 Rouge-1）和XSUM（49.07 Rouge-1）数据集上实现了新的最新结果。进一步的分析还表明，我们的模型可以估计与其质量水平更相关的候选摘要的概率。
Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to the reference summary. This assumption may lead to performance degradation during inference, where the model needs to compare several system-generated (candidate) summaries that have deviated from the reference summary. To address this problem, we propose a novel training paradigm which assumes a non-deterministic distribution so that different candidate summaries are assigned probability mass according to their quality. Our method achieves a new state-of-the-art result on the CNN/DailyMail (47.78 ROUGE-1) and XSum (49.07 ROUGE-1) datasets. Further analysis also shows that our model can estimate probabilities of candidate summaries that are more correlated with their level of quality.
