Matuszek, CynthiaFerraro, FrancisKery, Caroline Patricia2021-01-292021-01-292019-01-0112007http://hdl.handle.net/11603/20655In this theses I describe a multilingual grounded language learning system adapted from an English-only system. This system learns the meaning of words used in crowd-sourced descriptions by grounding them in the physical representations of the objects they are describing. My work compares the performance of the system between languages from different perspectives to identify modifications necessary to attain equal performance, with the goal of enhancing the ability of robots to learn language from a more diverse range of people. I first analyze Spanish using translated English data, and then extend this analysis to a new corpus crowd-sourced Spanish language data. I then take the insights gained from this analysis and repeat the experiment using Hindi. I find that with small modifications the system is able to learn color, object, and shape words with comparable performance between languages.application:pdfgrounded language acquisitionmultilingualText