3.dos Experiment 2: Contextual projection grabs good information regarding the interpretable object feature recommendations out-of contextually-constrained embeddings
3.dos Experiment 2: Contextual projection grabs good information regarding the interpretable object feature recommendations out-of contextually-constrained embeddings As predicted, combined-context embedding spaces’ performance was intermediate between the preferred and non-preferred CC embedding spaces in predicting human similarity judgments: as more nature semantic context data were used to train the combined-context models, the alignment between embedding […]