all AI news
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
April 2, 2024, 7:51 p.m. | Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki, Rico Sennrich, Yuval Pinter
cs.CL updates on arXiv.org arxiv.org
Abstract: We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not been subjected to rigorous scientific scrutiny. While the removal of rare subwords is suggested as best practice in machine translation implementations, both as a means to reduce model size and for improving model performance through robustness, our experiments indicate that, across a large …
abstract analysis arxiv cs.cl encoding explore libraries machine machine translation neural machine translation popular scientific threshold tokenization 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