mlsanityData to 14 Oct 2026

Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata

arXiv 2404.06854 ↗First posted 10 Apr 2024cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

The Directed Acyclic Transformer is a fast non-autoregressive (NAR) model that performs well in Neural Machine Translation. Two issues prevent its application to general Natural Language Generation (NLG) tasks: frequent Out-Of-Vocabulary (OOV) errors and the inability to faithfully generate entity names. We introduce Control-DAG, a constrained decoding algorithm for our Directed Acyclic T5 (DA-T5) model which offers lexical, vocabulary and length control. We show that Control-DAG significantly enhances DA-T5 on the Schema Guided Dialogue and the DART datasets, establishing strong NAR results for Task-Oriented Dialogue and Data-to-Text NLG.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

11 of 21 references.

References · 11

  1. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  2. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  3. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 182
  4. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  5. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
  6. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  7. 2021Guided Generation of Cause and Effectcited by 33
  8. 2022Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 13
  9. 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translationcited by 11
  10. 2023Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generationcited by 8
  11. 2023Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generationcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320