all AI news
On the True Distribution Approximation of Minimum Bayes-Risk Decoding
April 2, 2024, 7:51 p.m. | Atsumoto Ohashi, Ukyo Honda, Tetsuro Morimura, Yuu Jinnai
cs.CL updates on arXiv.org arxiv.org
Abstract: Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods. From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of …
abstract approximation arxiv attention bayes cs.ai cs.cl decoding distribution key risk sampling text text generation the key true 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
Business Data Analyst
@ Alstom | Johannesburg, GT, ZA