完整真相且仅此而已：基于数据流转导与受限解码的忠实可控对话回复生成
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
AI总结：
本文提出一种混合架构，结合数据流转导规则与受限解码，在神经语言模型生成中约束输出，实现既忠实又可控的对话回复生成，并在流畅性、相关性和真实性上超越现有方法。
摘要：
在现实世界的对话系统中，生成的文本必须真实且信息丰富，同时保持流畅并遵循规定的风格。同时满足这些约束对于语言生成中的两种主要范式——神经语言建模和基于规则的生成——而言是困难的。我们描述了一种用于对话回复生成的混合架构，该架构结合了两种范式的优势。该架构的第一个组件是基于规则的内容选择模型，该模型使用一种名为数据流转导（dataflow transduction）的新形式框架来定义，它使用声明性规则将对话代理的动作及其结果（表示为数据流图）转导为上下文无关文法，这些文法表示上下文可接受回复的空间。第二个组件是一种受限解码过程，它使用这些文法来约束神经语言模型的输出，从而选择流畅的话语。我们的实验表明，该系统在流畅性、相关性和真实性的评估中均优于基于规则的方法和基于学习的方法。
英文摘要：
In a real-world dialogue system, generated text must be truthful and informative while remaining fluent and adhering to a prescribed style. Satisfying these constraints simultaneously is difficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation. We describe a hybrid architecture for dialogue response generation that combines the strengths of both paradigms. The first component of this architecture is a rule-based content selection model defined using a new formal framework called dataflow transduction, which uses declarative rules to transduce a dialogue agent's actions and their results (represented as dataflow graphs) into context-free grammars representing the space of contextually acceptable responses. The second component is a constrained decoding procedure that uses these grammars to constrain the output of a neural language model, which selects fluent utterances. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
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。
