We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that often hallucinate information or generate summaries with coherence issues. To generate abstractive summaries with factual consistency and narrative flow, we propose Cooperative Generator -- Discriminator Networks (Co-opNet), a novel transformer-based framework where a generator works with a discriminator architecture to compose coherent long-form summaries. We explore four different discriminator objectives which each capture a different aspect of coherence, including whether salient spans of generated abstracts are hallucinated or appear in the input context, and the likelihood of sentence adjacency in generated abstracts. We measure the ability of Co-opNet to learn these objectives with arXiv scientific papers, using the abstracts as a proxy for gold long-form scientific article summaries. Empirical results from automatic and human evaluations demonstrate that Co-opNet learns to summarize with considerably improved global coherence compared to competitive baselines.
翻译:我们在产出摘要中引入一个抽象总结总框架,在事实上保持一致,对叙述流进行不同的建模; 我们的工作涉及目前抽象总结模型的局限性,这些模型往往产生幻觉信息,或产生带有一致性问题的概要; 为了产生具有事实一致性和叙述性流的抽象摘要, 我们提议合作生成者-分歧者网络(Co-opNet),这是一个全新的变压器框架,其中产生者与一个歧视者结构合作,编写连贯一致的长式摘要; 我们探讨四个不同的区别目标,其中每个目标都反映了一致性的不同方面,包括所生成的摘要的显著范围是幻觉还是出现在投入背景下,以及生成摘要中句的相似性的可能性; 我们用摘要作为黄金长式科学论文的代名,衡量共同运行网络用ArXiv科学论文学习这些目标的能力; 自动和人为评价的结果表明,共同运行网络学会了与竞争性基线相比,全球一致性大为改善。