论文标题
采取自然语言生成任务的务实生产策略
Towards Pragmatic Production Strategies for Natural Language Generation Tasks
论文作者
论文摘要
该立场论文提出了一个概念框架，用于遵循高效生产策略的自然语言生成（NLG）系统，以实现复杂的沟通目标。在这个一般框架中，效率的特征是对生产和理解成本的简约调节，而有效性是根据任务为导向和上下文扎根的沟通目标来衡量的。我们通过现代统计方法为目标，成本和实用性的估计提供了具体建议，并证明了我们框架的应用到视觉上扎根的参考游戏的经典务实任务以及抽象性文本摘要，这是两项具有现实世界应用的大众生成任务。总而言之，我们倡导开发NLG系统，这些系统学会通过以人类的方式来从经验中，对目标，成本和实用性进行推理，从经验中做出务实的生产决策。
This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order to achieve complex communicative goals. In this general framework, efficiency is characterised as the parsimonious regulation of production and comprehension costs while effectiveness is measured with respect to task-oriented and contextually grounded communicative goals. We provide concrete suggestions for the estimation of goals, costs, and utility via modern statistical methods, demonstrating applications of our framework to the classic pragmatic task of visually grounded referential games and to abstractive text summarisation, two popular generation tasks with real-world applications. In sum, we advocate for the development of NLG systems that learn to make pragmatic production decisions from experience, by reasoning about goals, costs, and utility in a human-like way.
