all AI news
Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata
April 11, 2024, 4:47 a.m. | Jinghong Chen, Weizhe Lin, Jingbiao Mei, Bill Byrne
cs.CL updates on arXiv.org arxiv.org
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 …
abstract application arxiv autoregressive control cs.cl dag decoding errors general generate language language generation machine machine translation natural natural language natural language generation neural machine translation nlg state tasks transformer translation type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Analyst (Digital Business Analyst)
@ Activate Interactive Pte Ltd | Singapore, Central Singapore, Singapore