2020/03/05 by Lucas Nunes Sequeira, Bruno Moreschi, Sequeira, Lucas Nunes +5
Computer Science · #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2003.02817
openalex publication_date 2020/03/05 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this research, we have established, through empirical testing, a law that\nrelates the number of translating hops to translation accuracy in sequential\nmachine translation in Google Translate. Both accuracy and size decrease with\nthe number of hops; the former displays a decrease closely following a power\nlaw. Such a law allows one to predict the behavior of translation chains that\nmay be built as society increasingly depends on automated devices.\n