Authors: Mariana Shimabukuro , Christopher Collins
Abstract: In this project, we present a visualization for investigating the relationship between commonly used words in Portuguese and their translations in English. This cross-linguistic analysis can help us to understand English word choices made by Portuguese native speakers and the influence of language transfer effects. In this paper, we discuss how word frequency is commonly used as a resource for both textual and cross-linguistic analysis. Moreover, we briefly explain the data processing pipeline building on machine translation and word frequencies from large corpora. This research reveals interesting open questions related to linguistic visualizations and future directions for investigating language transfer effects.