The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
This addresses the problem of ensuring faithful and controllable dialogue generation for real-world dialogue systems, representing an incremental improvement by hybridizing existing paradigms.
The paper tackles the challenge of generating dialogue responses that are simultaneously truthful, informative, fluent, and style-adherent by proposing a hybrid architecture combining rule-based dataflow transduction with neural language models and constrained decoding. Experiments show it outperforms rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
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.