用于多方对话响应生成的EM预训练
EM Pre-training for Multi-party Dialogue Response Generation
AI总结：
针对多方对话数据集缺乏听话者标签难以预训练响应生成模型的问题，提出迭代生成标签并优化模型的EM预训练方法，实验证明其可行有效。
摘要：
对话响应生成要求智能体根据当前对话历史生成响应，就此而言，双方对话已被充分研究，但多方对话仍存在巨大空白。与每条响应直接回复其上一条话语的双方对话不同，在多方场景中，生成响应话语前应先指定其听话者。得益于大量双方对话数据，已提出多种用于双方对话响应生成的预训练语言模型。然而，由于多方对话数据集缺乏标注的听话者标签，难以用其预训练多方对话响应生成模型。为克服此障碍，我们提出一种期望最大化（EM）方法，迭代执行期望步骤生成听话者标签，以及最大化步骤优化响应生成模型。理论分析与大量实验证明了所提方法的可行性与有效性。
英文摘要：
Dialogue response generation requires an agent to generate a response according to the current dialogue history, in terms of which two-party dialogues have been well studied, but leaving a great gap for multi-party dialogues at the same time. Different from two-party dialogues where each response is a direct reply to its previous utterance, the addressee of a response utterance should be specified before it is generated in the multi-party scenario. Thanks to the huge amount of two-party conversational data, various pre-trained language models for two-party dialogue response generation have been proposed. However, due to the lack of annotated addressee labels in multi-party dialogue datasets, it is hard to use them to pre-train a response generation model for multi-party dialogues. To tackle this obstacle, we propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels, and the maximization steps to optimize a response generation model. Theoretical analyses and extensive experiments have justified the feasibility and effectiveness of our proposed method.
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。
