Burns, AndreaKim, DonghyunWijaya, DerrySaenko, KatePlummer, Bryan A.Vedaldi, AndreaBischof, HorstBrox, ThomasFrahm, Jan-Michael2021-08-202021-08-202020Andrea Burns, Donghyun Kim, Derry Wijaya, Kate Saenko, Bryan A Plummer. 2020. "Learning to Scale Multilingual Representations for Vision-Language Tasks.." ECCV (4), Volume 12349, pp. 197 - 213.https://hdl.handle.net/2144/42930Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3-4% with less than 1/5th the training parameters compared to other word embedding methods.p. 197 - 213en-USScalable vision-language modelsMultilingual word embeddingsImage-sentence retrievalArticle572471