JADS：一种自监督的联合方面发现与摘要生成框架
JADS: A Framework for Self-supervised Joint Aspect Discovery and Summarization
AI总结：
JADS提出自监督框架，将方面发现与摘要生成整合为一步，优于两步基线，并通过预训练提升性能与稳定性，嵌入具有更强聚类能力。
摘要：
为了生成包含文本文档多个方面或主题的摘要，大多数方法使用聚类或主题建模来对相关句子进行分组，然后为每个组生成摘要。这些方法难以同时优化摘要生成和聚类算法。另一方面，基于方面的摘要生成需要已知的方面。我们的解决方案将主题发现和摘要生成整合为单一步骤。给定文本数据，我们的联合方面发现与摘要生成算法（JADS）从输入中发现方面，并一步生成主题摘要。我们提出了一种自监督框架，通过首先混合来自多个文档（例如CNN/DailyMail文章）的句子作为输入，然后使用混合后的文章摘要作为标签来创建带标签的数据集。JADS模型优于两步基线方法。通过预训练，模型获得了更好的性能和稳定性。此外，从JADS中获得的嵌入表现出卓越的聚类能力。我们提出的方法实现了与真实标签更高的语义对齐，并且是事实性的。
英文摘要：
To generate summaries that include multiple aspects or topics for text documents, most approaches use clustering or topic modeling to group relevant sentences and then generate a summary for each group. These approaches struggle to optimize the summarization and clustering algorithms jointly. On the other hand, aspect-based summarization requires known aspects. Our solution integrates topic discovery and summarization into a single step. Given text data, our Joint Aspect Discovery and Summarization algorithm (JADS) discovers aspects from the input and generates a summary of the topics, in one step. We propose a self-supervised framework that creates a labeled dataset by first mixing sentences from multiple documents (e.g., CNN/DailyMail articles) as the input and then uses the article summaries from the mixture as the labels. The JADS model outperforms the two-step baselines. With pretraining, the model achieves better performance and stability. Furthermore, embeddings derived from JADS exhibit superior clustering capabilities. Our proposed method achieves higher semantic alignment with ground truth and is factual.
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。
