End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of large pre-trained models, has further led to significant progress in EToD research in recent years. In this paper, we present a thorough review and provide a unified perspective to summarize existing approaches as well as recent trends to advance the development of EToD research. The contributions of this paper can be summarized: (1) $\mathit{\text{First}}\mathit{\text{survey}}$: to our knowledge, we take the first step to present a thorough survey of this research field; (2) $\mathit{\text{New}}\mathit{\text{taxonomy}}$: we first introduce a unified perspective for EToD, including (i) $\mathit{\text{Modularly}}\mathit{\text{EToD}}$ and (ii) $\mathit{\text{Fully}}\mathit{\text{EToD}}$; (3) $\mathit{\text{New}}\mathit{\text{Frontiers}}$: we discuss some potential frontier areas as well as the corresponding challenges, hoping to spur breakthrough research in EToD field; (4) $\mathit{\text{Abundant}}\mathit{\text{resources}}$: we build a public website\footnote{We collect the related papers, baseline projects, and leaderboards for the community at \url{https://etods.net/}.}, where EToD researchers could directly access the recent progress. We hope this work can serve as a thorough reference for the EToD research community.