no code implementations • 18 Aug 2013 • Yanpeng Li
Since the estimation of P(r|j)-P(r) does not require labeled data, under the assumption above, RDE trained with a large number of unlabeled examples would be close to that trained with infinite labeled examples.
no code implementations • COLING 2018 • Yanpeng Li
Representing a word by its co-occurrences with other words in context is an effective way to capture the meaning of the word.