all AI news
LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation
June 6, 2024, 4:52 a.m. | Zengkui Sun, Yijin Liu, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou
cs.CL updates on arXiv.org arxiv.org
Abstract: Multilingual neural machine translation models generally distinguish translation directions by the language tag (LT) in front of the source or target sentences. However, current LT strategies cannot indicate the desired target language as expected on zero-shot translation, i.e., the off-target issue. Our analysis reveals that the indication of the target language is sensitive to the placement of the target LT. For example, when placing the target LT on the decoder side, the indication would rapidly …
abstract analysis arxiv converter cs.ai cs.cl current front however issue language machine machine translation multilingual neural machine translation strategies strategy tag translation type zero-shot
More from arxiv.org / cs.CL updates on arXiv.org
LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?
1 day, 5 hours ago |
arxiv.org
mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs
1 day, 5 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Data Engineer
@ Displate | Warsaw
Senior Robotics Engineer - Applications
@ Vention | Montréal, QC, Canada
Senior Application Security Engineer, SHINE - Security Hub for Innovation and Efficiency
@ Amazon.com | Toronto, Ontario, CAN
Simulation Scientist , WWDE Simulation
@ Amazon.com | Bellevue, Washington, USA
Giáo Viên Steam
@ Việc Làm Giáo Dục | Da Nang, Da Nang, Vietnam
Senior Simulation Developer
@ Vention | Montréal, QC, Canada