通过顺序不敏感表示正则化实现鲁棒的个性化对话生成
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
AI总结：
针对个性化对话中人设句子输入顺序导致的模型性能波动问题，提出与模型无关的ORIG框架学习鲁棒表示，有效提升了GPT2和BART生成回复的一致性。
摘要：
生成符合人设的对话回复对于开发智能对话代理非常重要。近期的研究通常通过将人设文本和对话历史拼接为单一输入序列，对大规模预训练模型进行微调以生成目标回复。尽管这种方法简单有效，但我们的分析表明，这种流行做法严重受制于顺序敏感性：人设句子的不同输入顺序会显著影响生成回复的质量和一致性，导致严重的性能波动（即在GPT2上为29.4%，在BART上为83.2%）。为缓解顺序敏感性问题，我们提出了一个与模型无关的框架ORIG（顺序不敏感生成），使对话模型能够在不同人设顺序下学习鲁棒的表示，并提高回复生成的一致性。在Persona-Chat数据集上的实验证明，我们方法在使用GPT2和BART两种主流预训练模型时具有有效性和优越性。
英文摘要：
Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a single input sequence to generate the target response. While simple and effective, our analysis shows that this popular practice is seriously affected by order sensitivity where different input orders of persona sentences significantly impact the quality and consistency of generated response, resulting in severe performance fluctuations (i.e., 29.4% on GPT2 and 83.2% on BART). To mitigate the order sensitivity problem, we propose a model-agnostic framework, ORder Insensitive Generation (ORIG), which enables dialogue models to learn robust representation under different persona orders and improve the consistency of response generation. Experiments on the Persona-Chat dataset justify the effectiveness and superiority of our method with two dominant pre-trained models (GPT2 and BART).
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。
