MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies.
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023) LONG PAPERS, VOL 1（2023）
关键词
Language Modeling,Machine Translation,Topic Modeling,Statistical Language Modeling,Syntax-based Translation Models
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要