The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean, Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, Dan, Klein

TL;DR
This paper introduces a hybrid dialogue response generation system combining dataflow transduction and constrained decoding to produce truthful, relevant, and fluent responses, outperforming existing methods.
Contribution
It proposes a novel hybrid architecture that integrates rule-based content selection with neural language models using dataflow transduction and constrained decoding.
Findings
Outperforms rule-based and learned approaches in human evaluations.
Produces more truthful and relevant responses.
Maintains high fluency in generated dialogue.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Speech and dialogue systems
