Patricio Cerda-Mardini author Vladimir Araujo author Álvaro Soto author 2020-jul text Association for Computational Linguistics Seattle, USA conference publication We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navigation. We follow the framework established by (Zang et al., 2018a) that proposes the use of a navigation graph as a knowledge base for the task. Our results show significant performance gains when translating instructions on previously unseen environments, therefore, improving the generalization capabilities of the model. cerda-mardini-etal-2020-translating 2020-jul 96 98