all AI news
Tokenization Preference for Human and ML Model: An Annotation Study
Feb. 16, 2024, 5:48 a.m. | Tatsuya Hiraoka, Tomoya Iwakura
cs.CL updates on arXiv.org arxiv.org
Abstract: Is preferred tokenization for humans also preferred for machine-learning (ML) models? This study examines the relations between preferred tokenization for humans (appropriateness and readability) and one for ML models (performance on an NLP task). The question texts of the Japanese commonsense question-answering dataset are tokenized with six different tokenizers, and the performances of human annotators and ML models were compared. Furthermore, we analyze relations among performance of answers by human and ML model, the appropriateness …
abstract annotation arxiv cs.cl dataset human humans japanese machine ml models nlp performance question readability relations study tokenization type
More from arxiv.org / cs.CL updates on arXiv.org
Benchmarking LLMs via Uncertainty Quantification
1 day, 18 hours ago |
arxiv.org
CARE: Extracting Experimental Findings From Clinical Literature
1 day, 18 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
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
Director, Clinical Data Science
@ Aura | Remote USA
Research Scientist, AI (PhD)
@ Meta | Menlo Park, CA | New York City