谁说得像 Vitamin 的风格：利用多任务学习实现句法感知的对话摘要
Who speaks like a style of Vitamin: Towards Syntax-Aware DialogueSummarization using Multi-task Learning
AI总结：
针对对话信息分散且语体非正式的问题，本文提出融合 POS tagging 的句法感知多任务学习模型，用于区分说话者风格并提升生成式对话摘要性能。
摘要：
生成式对话摘要之所以是一项具有挑战性的任务，有多个原因。首先，对话中的大多数重要信息通过具有不同文本风格的多方交互散布在各个话语中。其次，对话通常是非正式结构，不同的人在其中表达个人观点，这不同于通常以新闻文章等正式文档为目标的文本摘要任务。为了解决这些问题，我们关注来自单个说话者的话语与独特句法结构之间的关联。说话者具有独特的文本风格，其中可以包含诸如声纹之类的语言信息。因此，我们利用语言信息（即 POS tagging，词性标注）构建了一个句法感知模型，该模型通过从本质上区分单个说话者所说的句子来缓解上述问题。我们采用了句法感知信息和对话摘要的多任务学习。据我们所知，我们的方法是首个将多任务学习应用于对话摘要任务的方法。在 SAMSum 语料库（一个大规模对话摘要语料库）上的实验表明，我们的方法相对于普通模型有所改进。我们进一步分析了我们的方法相对于基线模型的成本与收益。
英文摘要：
Abstractive dialogue summarization is a challenging task for several reasons. First, most of the important pieces of information in a conversation are scattered across utterances through multi-party interactions with different textual styles. Second, dialogues are often informal structures, wherein different individuals express personal perspectives, unlike text summarization, tasks that usually target formal documents such as news articles. To address these issues, we focused on the association between utterances from individual speakers and unique syntactic structures. Speakers have unique textual styles that can contain linguistic information, such as voiceprint. Therefore, we constructed a syntax-aware model by leveraging linguistic information (i.e., POS tagging), which alleviates the above issues by inherently distinguishing sentences uttered from individual speakers. We employed multi-task learning of both syntax-aware information and dialogue summarization. To the best of our knowledge, our approach is the first method to apply multi-task learning to the dialogue summarization task. Experiments on a SAMSum corpus (a large-scale dialogue summarization corpus) demonstrated that our method improved upon the vanilla model. We further analyze the costs and benefits of our approach relative to baseline models.
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。
