@inproceedings{ji-etal-2025-tree,
    title = "Tree-Structured Non-Autoregressive Decoding for Sequence-to-Sequence Text Generation",
    author = "Ji, Pengyu  and
      Liu, Yufei  and
      Hu, Xiang  and
      Tu, Kewei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.327/",
    doi = "10.18653/v1/2025.findings-emnlp.327",
    pages = "6168--6174",
    ISBN = "979-8-89176-335-7",
    abstract = "Autoregressive Transformer (AT) dominates sequence-to-sequence generation tasks but suffers from high inference latency due to sequential token generation. Non-Autoregressive Transformer (NAT) improves inference efficiency by parallelizing token prediction, yet degrades generation quality. To address these limitations, we propose Tree-structured Non-Autoregressive Decoding (TNAD), a novel paradigm that bridges autoregressive and non-autoregressive decoding. TNAD generates a sentence through a top-down, layer-wise expansion of its constituency parse tree, enabling parallel generation within each layer while preserving contextual dependencies across layers. Experimental results on machine translation and paraphrase generation demonstrate that TNAD outperforms AT in efficiency and NAT in generation quality, thus offering a new alternative to AT and NAT in the trade-off between efficiency and quality. Our code is publicly available at \url{https://github.com/jipy0222/TNAD}."
}