BoK：引入关键词袋损失用于可解释对话回复生成
BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation
AI总结：
针对标准语言建模损失不足以支撑对话建模的问题，提出关键词袋（BoK）辅助损失，通过预测下轮话语关键词增强回复生成的质量与可解释性，在两类架构及多个数据集上验证了有效性与指标潜力。
摘要：
标准语言建模（LM）损失本身已被证明不足以实现有效的对话建模。因此，各类训练方法（如辅助损失函数、利用人类反馈）正被用于丰富开放域对话系统。词袋（BoW）损失便是这类辅助损失函数之一，其定义为预测下一轮话语所有词/词元的交叉熵损失。本研究中，我们提出一种名为关键词袋（BoK）损失的新型辅助损失，通过关键词预测捕捉回复的核心思想，并利用该损失提升开放域对话系统中意义明确、可解释回复的生成效果。BoK损失对BoW损失进行了升级，仅预测下一轮话语的关键词或关键的词/词元，旨在估计核心思想而非完整回复。我们将BoK损失融入编码器-解码器（T5）架构与仅解码器（DialoGPT）架构中，训练模型以最小化BoK与LM（BoK-LM）损失的加权和。我们在两个主流开放域对话数据集DailyDialog和Persona-Chat上开展实验。结果表明，加入BoK损失可改善骨干模型的对话生成效果，同时还能实现事后可解释性。我们还研究了BoK-LM损失作为无参考指标的有效性，发现在多个对话评估数据集上，其性能与当前最优指标相当。
英文摘要：
The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted to enrich open-domain dialogue systems. One such auxiliary loss function is Bag-of-Words (BoW) loss, defined as the cross-entropy loss for predicting all the words/tokens of the next utterance. In this work, we propose a novel auxiliary loss named Bag-of-Keywords (BoK) loss to capture the central thought of the response through keyword prediction and leverage it to enhance the generation of meaningful and interpretable responses in open-domain dialogue systems. BoK loss upgrades the BoW loss by predicting only the keywords or critical words/tokens of the next utterance, intending to estimate the core idea rather than the entire response. We incorporate BoK loss in both encoder-decoder (T5) and decoder-only (DialoGPT) architecture and train the models to minimize the weighted sum of BoK and LM (BoK-LM) loss. We perform our experiments on two popular open-domain dialogue datasets, DailyDialog and Persona-Chat. We show that the inclusion of BoK loss improves the dialogue generation of backbone models while also enabling post-hoc interpretability. We also study the effectiveness of BoK-LM loss as a reference-free metric and observe comparable performance to the state-of-the-art metrics on various dialogue evaluation datasets.
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。
