Distributional Modeling on a Diet: One-shot Word Learning from Text Only
This addresses the challenge of efficient word learning in natural language processing, but it is incremental as it builds on existing distributional and Bayesian methods.
The paper tackles the problem of one-shot learning of definitional properties from text using distributional models, finding that Bayesian models leveraging overarching structure and informative contexts enable learning from a single exposure.
We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative. Our experiments show that our model can learn properties from a single exposure when given an informative utterance.