Word2vec to behavior: morphology facilitates the grounding of language in machines
This addresses the problem of grounding language in embodied machines for broader service applications, but it appears incremental as it builds on existing word2vec methods.
The paper tackled the problem of enabling robots to respond to natural language commands by training them to act similarly to semantically-similar word2vec encoded commands, resulting in the robots acting appropriately to previously-unheard commands after training.
Enabling machines to respond appropriately to natural language commands could greatly expand the number of people to whom they could be of service. Recently, advances in neural network-trained word embeddings have empowered non-embodied text-processing algorithms, and suggest they could be of similar utility for embodied machines. Here we introduce a method that does so by training robots to act similarly to semantically-similar word2vec encoded commands. We show that this enables them to act appropriately, after training, to previously-unheard commands. Finally, we show that inducing such an alignment between motoric and linguistic similarities can be facilitated or hindered by the mechanical structure of the robot. This points to future, large scale methods that find and exploit relationships between action, language, and robot structure.