可控主题聚焦的抽象式摘要生成
Controllable Topic-Focused Abstractive Summarization
AI总结：
本文提出一种基于Transformer的交叉注意力修改机制，在不增加参数的情况下实现可控主题聚焦摘要，在NEWTS数据集上达到新最优，并可微调提升BART和T5在CNN/Dailymail及XSum上的性能，生成更忠实的摘要。
摘要：
受控抽象式摘要生成旨在通过将生成文本的分布向期望风格（例如一组主题）偏移，从而生成源文章的压缩版本以覆盖特定方面。由此产生的摘要可进一步根据用户定义的需求进行定制。本文提出了一种新的基于Transformer的架构，能够生成主题聚焦的摘要。该架构修改了Transformer的交叉注意力机制，在不向模型添加任何额外参数的情况下，将主题聚焦控制引入生成过程。我们展示了我们的模型在NEWTS数据集上，在主题聚焦抽象式摘要以及主题流行度得分方面均达到了新的最先进水平。此外，通过大量实验，我们证明了所提出的主题交叉注意力机制可以嵌入到各种Transformer模型中，如BART和T5，提升它们在CNN/Dailymail和XSum基准数据集上的抽象式摘要性能。这是通过微调实现的，无需从头训练。最后，通过人工评估，我们表明我们的模型生成的摘要更加忠实，优于最先进的Frost模型。
英文摘要：
Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects by shifting the distribution of generated text towards a desired style, e.g., a set of topics. Subsequently, the resulting summaries may be tailored to user-defined requirements. This paper presents a new Transformer-based architecture capable of producing topic-focused summaries. The architecture modifies the cross-attention mechanism of the Transformer to bring topic-focus control to the generation process while not adding any further parameters to the model. We show that our model sets a new state of the art on the NEWTS dataset in terms of topic-focused abstractive summarization as well as a topic-prevalence score. Moreover, we show via extensive experiments that our proposed topical cross-attention mechanism can be plugged into various Transformer models, such as BART and T5, improving their performance on the CNN/Dailymail and XSum benchmark datasets for abstractive summarization. This is achieved via fine-tuning, without requiring training from scratch. Finally, we show through human evaluation that our model generates more faithful summaries outperforming the state-of-the-art Frost model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
