Joint translation and unit conversion for end-to-end localization

2020/04/10 by Dinu, Georgiana, Mathur, Prashant, Federico, Marcello +2 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2004.05219

Abstract

A variety of natural language tasks require processing of textual data which contains a mix of natural language and formal languages such as mathematical expressions. In this paper, we take unit conversions as an example and propose a data augmentation technique which leads to models learning both translation and conversion tasks as well as how to adequately switch between them for end-to-end localization.

Cited by

• On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures

Related

• Exploiting Similarities among Languages for Machine Translation
• Back Translation Survey for Improving Text Augmentation
• Document-Level Language Models for Machine Translation
• Using Machine Translation to Localize Task Oriented NLG Output
• Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data