CONFIT：面向忠实对话摘要的语言学信息对比微调
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
AI总结：
针对对话摘要中的事实不一致问题，提出基于语言学错误类型学的对比微调方法ConFiT，通过模块化目标和对话特定损失显著减少幻觉，并在SAMSum和AMI数据集上超越多数基线。
摘要：
生成摘要中的事实不一致严重限制了抽象式对话摘要的实际应用。尽管使用预训练模型已取得了显著进展，但在人工评估中仍发现大量幻觉内容。预训练模型最常用的微调方式是针对文本摘要的交叉熵损失，这可能并非最优策略。在本工作中，我们提供了一种带有标注数据的事实错误类型学，以突出错误类型并摆脱对事实性的二元理解。我们进一步提出了一种训练策略，通过一种新颖的对比微调方法（称为ConFiT）来提高摘要的事实一致性和整体质量。基于我们语言学信息驱动的错误类型学，我们设计了不同的模块化目标，每个目标针对特定类型。具体而言，我们利用带有错误的硬负样本以减少事实不一致的生成。为了捕捉说话者之间的关键信息，我们还设计了一种对话特定的损失。通过人工评估和自动忠实度指标，我们表明我们的模型显著减少了对话摘要（SAMSum语料库）上的所有类型的事实错误。此外，我们的模型可以泛化到会议摘要（AMI语料库），并且在两个数据集上，就词重叠指标而言，其得分显著高于大多数基线。
英文摘要：
Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated content are found during the human evaluation. Pre-trained models are most commonly fine-tuned with cross-entropy loss for text summarization, which may not be an optimal strategy. In this work, we provide a typology of factual errors with annotation data to highlight the types of errors and move away from a binary understanding of factuality. We further propose a training strategy that improves the factual consistency and overall quality of summaries via a novel contrastive fine-tuning, called ConFiT. Based on our linguistically-informed typology of errors, we design different modular objectives that each target a specific type. Specifically, we utilize hard negative samples with errors to reduce the generation of factual inconsistency. In order to capture the key information between speakers, we also design a dialogue-specific loss. Using human evaluation and automatic faithfulness metrics, we show that our model significantly reduces all kinds of factual errors on the dialogue summarization, SAMSum corpus. Moreover, our model could be generalized to the meeting summarization, AMI corpus, and it produces significantly higher scores than most of the baselines on both datasets regarding word-overlap metrics.
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。
