Controlling Dialogue Generation with Semantic Exemplars

Prakhar Gupta, Jeffrey Bigham, Yulia Tsvetkov, Amy Pavel
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   unpublished
Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A promising method for controlling generated responses is exemplar-based generation, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. We present an Exemplar-based Dialogue GEneration model, EDGE,
more » ... tion model, EDGE, that uses the semantic frames present in exemplar responses to guide response generation. We show that controlling dialogue generation based on the semantic frames of exemplars improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar re-1 sponses.
doi:10.18653/v1/2021.naacl-main.240 fatcat:zf7rh2zwkjgy7egez5agnz7n3m