基于查询聚合的指令式对话摘要
Instructive Dialogue Summarization with Query Aggregations
AI总结：
本文针对对话摘要未考虑用户特定兴趣的问题，提出通过三步合成查询式摘要数据并训练统一模型InstructDS，在多个数据集上超越现有模型，提升了泛化性与忠实度。
摘要：
传统的对话摘要方法直接生成摘要，并未考虑用户的具体兴趣，这在用户更关注特定主题或方面时会带来挑战。随着指令微调语言模型的发展，我们将指令微调引入对话任务，以扩展对话摘要模型的能力范围。为克服指令式对话摘要数据稀缺的问题，我们提出了一种三步方法来合成高质量的基于查询的摘要三元组。该过程包括以摘要为锚点的查询生成、查询过滤以及基于查询的摘要生成。通过在三个摘要数据集上使用多用途指令三元组训练一个名为InstructDS（指令式对话摘要）的统一模型，我们扩展了对话摘要模型的能力。我们在四个数据集上评估了该方法，涵盖对话摘要和对话阅读理解任务。实验结果表明，我们的方法优于最先进的模型，甚至优于规模更大的模型。此外，人类主观评估证实，我们的模型展现出更高的泛化能力和忠实度。
英文摘要：
Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests. This poses challenges in cases where the users are more focused on particular topics or aspects. With the advancement of instruction-finetuned language models, we introduce instruction-tuning to dialogues to expand the capability set of dialogue summarization models. To overcome the scarcity of instructive dialogue summarization data, we propose a three-step approach to synthesize high-quality query-based summarization triples. This process involves summary-anchored query generation, query filtering, and query-based summary generation. By training a unified model called InstructDS (Instructive Dialogue Summarization) on three summarization datasets with multi-purpose instructive triples, we expand the capability of dialogue summarization models. We evaluate our method on four datasets, including dialogue summarization and dialogue reading comprehension. Experimental results show that our approach outperforms the state-of-the-art models and even models with larger sizes. Additionally, our model exhibits higher generalizability and faithfulness, as confirmed by human subjective evaluations.
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。
