论文标题
知识以语义驱动的披风奖励图形提示抽象摘要
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
论文作者
论文摘要
已经对抽象性摘要的序列到序列模型进行了广泛的研究，但生成的摘要通常遭受捏造的内容的影响，并且经常被发现几乎具有提取性。我们认为，为了解决这些问题，摘要器应通过结构化表示，以获取语义解释，以允许产生更有益的摘要。在本文中，我们介绍了Asgard，这是一个新颖的框架，用于以图形振动和语义驱动的奖励进行抽象性汇总。我们建议使用双重编码器---一个顺序文档编码器和图形结构化编码器 - - 维护实体的全局上下文和本地特征，相互补充。我们进一步设计了基于多项选择披肩测试的奖励，以推动模型以更好地捕获实体交互。结果表明，与没有知识图的变体相比，我们的模型产生的胭脂得分明显更高，因为New York Times和CNN/Daily Mail数据集的输入。与从大型验证语言模型进行微调的系统相比，我们还获得了更好或可比的性能。人类法官将我们的模型输出进一步评估为更有信息，并且包含更少的不忠错误。
Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive. We argue that, to address these issues, the summarizer should acquire semantic interpretation over input, e.g., via structured representation, to allow the generation of more informative summaries. In this paper, we present ASGARD, a novel framework for Abstractive Summarization with Graph-Augmentation and semantic-driven RewarD. We propose the use of dual encoders---a sequential document encoder and a graph-structured encoder---to maintain the global context and local characteristics of entities, complementing each other. We further design a reward based on a multiple choice cloze test to drive the model to better capture entity interactions. Results show that our models produce significantly higher ROUGE scores than a variant without knowledge graph as input on both New York Times and CNN/Daily Mail datasets. We also obtain better or comparable performance compared to systems that are fine-tuned from large pretrained language models. Human judges further rate our model outputs as more informative and containing fewer unfaithful errors.
