{
  "id": "cascaded2020",
  "title": "Cascaded Text Generation with Markov Transformers",
  "authors": [
    {
      "given": "Yuntian",
      "family": "Deng"
    },
    {
      "given": "Alexander M.",
      "family": "Rush"
    }
  ],
  "year": 2020,
  "venue": "NeurIPS 2020",
  "paper_url": "https://arxiv.org/abs/2006.01112",
  "pdf_url": "https://papers.nips.cc/paper/2020/file/01a0683665f38d8e5e567b3b15ca98bf-Paper.pdf",
  "code_url": "https://github.com/harvardnlp/cascaded-generation",
  "summary": "Higher-order CRF cascades for parallel text generation, parameterized by one Markov Transformer.",
  "connection": "Increasing output dependence with tractable structured inference connects to joint modeling inside diffusion decoding.",
  "bibtex_type": "inproceedings",
  "citation_key": "deng2020cascaded",
  "source_urls": [
    "https://arxiv.org/abs/2006.01112",
    "https://arxiv.org/html/2006.01112v2"
  ],
  "arxiv_id": "2006.01112",
  "arxiv_first_posted": "2020-06-01",
  "abstract": "The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies. This work proposes an autoregressive model with sub-linear parallel time generation. Noting that conditional random fields with bounded context can be decoded in parallel, we propose an efficient cascaded decoding approach for generating high-quality output. To parameterize this cascade, we introduce a Markov transformer, a variant of the popular fully autoregressive model that allows us to simultaneously decode with specific autoregressive context cutoffs. This approach requires only a small modification from standard autoregressive training, while showing competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.",
  "abstract_source": "https://arxiv.org/html/2006.01112v2",
  "updated_at": "2026-11-10",
  "record_url": "https://yuntiandeng.com/research/papers/cascaded2020/"
}