@inproceedings{fang2023the,
author = {Fang, Hao and Balakrishnan, Anusha and Jhamtani, Harsh and Bufe, John and Crawford, Jean and Krishnamurthy, Jayant and Pauls, Adam and Eisner, Jason and Andreas, Jacob and Klein, Dan},
title = {The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding},
booktitle = {Findings of ACL 2023},
year = {2023},
month = {July},
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 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.},
url = {http://approjects.co.za/?big=en-us/research/publication/the-whole-truth-and-nothing-but-the-truth-faithful-and-controllable-dialogue-response-generation-with-dataflow-transduction-and-constrained-decoding/},
}