all AI news
Generating Diverse Translation with Perturbed kNN-MT
Feb. 15, 2024, 5:46 a.m. | Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe
cs.CL updates on arXiv.org arxiv.org
Abstract: Generating multiple translation candidates would enable users to choose the one that satisfies their needs. Although there has been work on diversified generation, there exists room for improving the diversity mainly because the previous methods do not address the overcorrection problem -- the model underestimates a prediction that is largely different from the training data, even if that prediction is likely. This paper proposes methods that generate more diverse translations by introducing perturbed k-nearest neighbor …
abstract arxiv cs.cl diverse diversity knn multiple prediction room translation type work
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote