NAACL 2024short2 citations

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

Jinghong Chen, Weizhe Lin, Jingbiao Mei, Bill Byrne

Abstract

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.

BibTeX
@inproceedings{chen-etal-2024-control,
    title = "Control-{DAG}: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata",
    author = "Chen, Jinghong  and
      Lin, Weizhe  and
      Mei, Jingbiao  and
      Byrne, Bill",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-short.42/",
    doi = "10.18653/v1/2024.naacl-short.42",
    pages = "508--518"
}
Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata · NAACL 2024