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.

提出了一种新的非确定性分布训练方法，通过根据其质量分配概率质量到不同的候选摘要，从而解决确定性分布训练方法在推断时导致的性能下降问题， 在 CNN/DailyMail 和 XSum 数据集上均取得了优于现有方法的最优结果，并且与质量水平更相关的评估摘要的概率评估。

BRIO：让抽象化摘要更有序

BRIO: Bringing Order to Abstractive Summarization

We propose a new approach to generate multiple variants of the target summary
with diverse content and varying lengths, then score and select admissible ones
according to users' needs. Abstractive summarizers trained on single reference
summaries may struggle to produce outputs that achieve multiple desirable
properties, i.e., capturing the most important information, being faithful to
the original, grammatical and fluent. In this paper, we propose a two-staged
strategy to generate a diverse set of candidate summaries from the source text
in stage one, then score and select admissible ones in stage two. Importantly,
our generator gives a precise control over the length of the summary, which is
especially well-suited when space is limited. Our selectors are designed to
predict the optimal summary length and put special emphasis on faithfulness to
the original text. Both stages can be effectively trained, optimized and
evaluated. Our experiments on benchmark summarization datasets suggest that
this paradigm can achieve state-of-the-art performance.

本研究提出一种新方法，通过生成多个变体的目标摘要，这些摘要具有不同的内容和不同的长度，并根据用户的需要进行评分和选择，该方法可用于控制摘要长度，从而实现最佳的信息概括，保证真实性并确保流畅。

一种新的从容提取摘要的方法

A New Approach to Overgenerating and Scoring Abstractive Summaries

Existing multi-document summarization systems usually rely on a specific
summarization model (i.e., a summarization method with a specific parameter
setting) to extract summaries for different document sets with different
topics. However, according to our quantitative analysis, none of the existing
summarization models can always produce high-quality summaries for different
document sets, and even a summarization model with good overall performance may
produce low-quality summaries for some document sets. On the contrary, a
baseline summarization model may produce high-quality summaries for some
document sets. Based on the above observations, we treat the summaries produced
by different summarization models as candidate summaries, and then explore
discriminative reranking techniques to identify high-quality summaries from the
candidates for difference document sets. We propose to extract a set of
candidate summaries for each document set based on an ILP framework, and then
leverage Ranking SVM for summary reranking. Various useful features have been
developed for the reranking process, including word-level features,
sentence-level features and summary-level features. Evaluation results on the
benchmark DUC datasets validate the efficacy and robustness of our proposed
approach.

本文提出了基于 ILP 框架提取每个文档集的一组候选摘要，然后利用排名 SVM 进行摘要重新排名的方法，结果通过 DUC 基准数据集验证了方法的有效性和鲁棒性。