English

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

Computation and Language 2022-09-27 v2

Abstract

We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs. The model features a new response selection method based on an action-aware training objective and a simplified single-encoder retrieval architecture which allow us to build an end-to-end retrieval-enhanced generation model where retrieval and generation share most of the parameters. On the MultiWOZ dataset, we show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance, compared to state-of-the-art baselines.

Keywords

Cite

@article{arxiv.2209.03632,
  title  = {AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog},
  author = {Tomáš Nekvinda and Ondřej Dušek},
  journal= {arXiv preprint arXiv:2209.03632},
  year   = {2022}
}

Comments

SIGDIAL 2022, with updated examples in Table 4

R2 v1 2026-06-28T00:56:13.421Z