Learning to Mediate Disparities Towards Pragmatic Communication
Learning to Mediate Disparities Towards Pragmatic Communication
复制标题
DOI：
10.48550/arxiv.2203.13685
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Yuwei Bao;Sayan Ghosh;J. Chai
中科院分区：
文献类型：
--
作者：
Yuwei Bao;Sayan Ghosh;J. Chai
人际沟通是一个协作的过程。说话者在传达自己意图的同时，还根据听者的知识背景、个性和身体能力等因素调整内容和语言表达。为了构建具有类似语言交流能力的人工智能代理，我们提出了一种新的理性推理框架，语用理性扬声器（PRS），扬声器试图学习说话者-听者差异并相应地调整语音，通过在扬声器的长期记忆系统之上添加一个轻量级的差异调整层到工作记忆中。通过固定长期记忆，PRS只需要更新其工作记忆来学习和适应不同类型的听者。为了验证我们的框架，我们创建了一个数据集，模拟不同类型的说者-听者的差异的背景下，参考游戏。我们的实证结果表明，PRS能够将其输出转向听众能够理解的语言，显着提高协作任务的结果，并比联合训练更有效地学习差异。
Human communication is a collaborative process. Speakers, on top of conveying their own intent, adjust the content and language expressions by taking the listeners into account, including their knowledge background, personalities, and physical capabilities. Towards building AI agents with similar abilities in language communication, we propose a novel rational reasoning framework, Pragmatic Rational Speaker (PRS), where the speaker attempts to learn the speaker-listener disparity and adjust the speech accordingly, by adding a light-weighted disparity adjustment layer into working memory on top of speaker’s long-term memory system. By fixing the long-term memory, the PRS only needs to update its working memory to learn and adapt to different types of listeners. To validate our framework, we create a dataset that simulates different types of speaker-listener disparities in the context of referential games. Our empirical results demonstrate that the PRS is able to shift its output towards the language that listeners are able to understand, significantly improve the collaborative task outcome, and learn the disparity more efficiently than joint training.