论文标题
我听起来像我吗？通过务实的自我意识改善对话中角色的一致性
Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness
论文作者
论文摘要
我们探讨了提高对话代理人角色一致性的任务。最近的模型应对一致性通常使用其他自然语言推断（NLI）标签训练，或将经过训练的额外模块附加到生成剂以维持一致性。但是，这种其他标签和培训可能要求。此外，我们发现，即使是表现最好的角色代理也对矛盾的词不敏感。受社会认知和实用主义者的启发，我们通过虚构的听众赋予了现有的对话代理人的公共自我意识。我们的方法基于理性的演讲框架（Frank and Goodman，2012年），可以强制执行对话代理，以免说出矛盾。我们通过学习干扰物选择，进一步扩展框架，这些选择通常是手动或随机完成的。对话NLI（Welleck等人，2019年）和《人类法》（Zhang等，2018）数据集的结果表明，我们的方法减少了矛盾并提高了现有对话模型的一致性。此外，我们证明它可以推广以提高对话中的情境之外的上下文一致性。
We explore the task of improving persona consistency of dialogue agents. Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for maintaining consistency. However, such additional labels and training can be demanding. Also, we find even the best-performing persona-based agents are insensitive to contradictory words. Inspired by social cognition and pragmatics, we endow existing dialogue agents with public self-consciousness on the fly through an imaginary listener. Our approach, based on the Rational Speech Acts framework (Frank and Goodman, 2012), can enforce dialogue agents to refrain from uttering contradiction. We further extend the framework by learning the distractor selection, which has been usually done manually or randomly. Results on Dialogue NLI (Welleck et al., 2019) and PersonaChat (Zhang et al., 2018) dataset show that our approach reduces contradiction and improves consistency of existing dialogue models. Moreover, we show that it can be generalized to improve context-consistency beyond persona in dialogues.
