论文标题
关于抽象性摘要的可区分n-gram目标
Differentiable N-gram Objective on Abstractive Summarization
论文作者
论文摘要
Rouge是基于序列到序列任务的n-gram的标准自动评估度量，而跨膜片损失是神经网络语言模型的基本目标，可在米格拉姆级别进行优化。我们提出了可区分的N-Gram目标，试图减轻培训标准和评估标准之间的差异。目的使匹配的子序列的概率权重最大化，我们工作的新颖性是客观的权重，匹配的子序列均等，并未通过参考序列中的n-gram的地面真实计数来表达匹配的子序列的数量。我们共同优化了跨凝结损失和提议的目标，从抽象性摘要数据集CNN/DM和XSUM提供了体面的胭脂评分增强，优于替代N-gram目标。
ROUGE is a standard automatic evaluation metric based on n-grams for sequence-to-sequence tasks, while cross-entropy loss is an essential objective of neural network language model that optimizes at a unigram level. We present differentiable n-gram objectives, attempting to alleviate the discrepancy between training criterion and evaluating criterion. The objective maximizes the probabilistic weight of matched sub-sequences, and the novelty of our work is the objective weights the matched sub-sequences equally and does not ceil the number of matched sub-sequences by the ground truth count of n-grams in reference sequence. We jointly optimize cross-entropy loss and the proposed objective, providing decent ROUGE score enhancement over abstractive summarization dataset CNN/DM and XSum, outperforming alternative n-gram objectives.
