We propose a model based on context encoder to solve formal analogies on strings like aaabbbccc : aaaabbbhcccc :: abc : x → x = aabbcc or ubid : tubid :: offid : x → x = tofjid. As a context encoder model, it consists of a generator and a discriminator. The generator attempts at generating the result of an analogical equation, while the discriminator attempts at discriminating solutions coming out of the generator against the real solution of the analogical equation. We conduct experiments on publicly available data sets to compare the performance of our model with a previously published method designed for the same task. Our results show slight increases in accuracy, in comparison to a fully connected neural network architecture.
展开▼
