David Vandyke

2 accepted papers

2024

TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles

Yinhong Liu, Yimai Fang, David Vandyke, Nigel Collier

ACL 2024findings

In light of recent advances in large language models (LLMs), the expectations for the next generation of virtual assistants include enhanced naturalness and adaptability across diverse usage scenarios. However, the creation of high-quality annotated data for Task-Oriented Dialog (TOD) is recognized…

Cited by 7 Source ↗PDF ↗Scholar ↗

2021

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

Yixuan Su, David Vandyke, Sihui Wang, Yimai Fang, Nigel Collier

EMNLP 2021finding

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, we propose a novel Plan-then-Generate (PlanGen) fra…

Cited by 84 Source ↗PDF ↗Scholar ↗