Simulated robots evolved with word2vec-initialized recurrent controllers can respond correctly to an unseen synonym of a training command, and the robot's body morphology changes how well this grounding works.
Support vector machines and word2vec for text classification with semantic features,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Word2vec to behavior: morphology facilitates the grounding of language in machines
Simulated robots evolved with word2vec-initialized recurrent controllers can respond correctly to an unseen synonym of a training command, and the robot's body morphology changes how well this grounding works.