主题可控摘要生成：主题感知评估与Transformer方法
Topic-Controllable Summarization: Topic-Aware Evaluation and Transformer Methods
AI总结：
针对主题可控摘要生成现有方法性能受限、缺乏专用评估指标的问题，本研究提出主题导向评估指标，以及基于Transformer、通过控制令牌引导生成的高效方法，性能更优且速度更快。
摘要：
主题可控摘要生成是一个新兴研究领域，具备广泛的潜在应用场景。然而现有方法存在显著局限性：例如，大多数现有方法基于循环架构构建，与更新的基于Transformer的架构相比，其性能受到明显限制，且这类方法还需要修改模型架构才能实现主题控制。同时，目前尚无专门针对主题可控摘要生成的成熟评估指标。本研究提出了一种新的面向主题的评估指标，可基于生成摘要与目标主题之间的主题亲和度，自动评估生成的摘要。通过合理设计的人工评估，验证了该指标的可靠性。此外，我们将主题嵌入适配到性能强大的Transformer架构中，并提出了一种新颖高效的方法，通过控制令牌引导摘要生成过程。实验结果表明，与更复杂的基于嵌入的方法相比，控制令牌方法能取得更优的性能，同时速度也显著更快。
英文摘要：
Topic-controllable summarization is an emerging research area with a wide range of potential applications. However, existing approaches suffer from significant limitations. For example, the majority of existing methods built upon recurrent architectures, which can significantly limit their performance compared to more recent Transformer-based architectures, while they also require modifications to the model's architecture for controlling the topic. At the same time, there is currently no established evaluation metric designed specifically for topic-controllable summarization. This work proposes a new topic-oriented evaluation measure to automatically evaluate the generated summaries based on the topic affinity between the generated summary and the desired topic. The reliability of the proposed measure is demonstrated through appropriately designed human evaluation. In addition, we adapt topic embeddings to work with powerful Transformer architectures and propose a novel and efficient approach for guiding the summary generation through control tokens. Experimental results reveal that control tokens can achieve better performance compared to more complicated embedding-based approaches while also being significantly faster.
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。
