A neural network for interpretation of multi-meaning words

A neural network is proposed that can interpret words with multiple meanings correctly by using contextual information. The network learns to recognize its present context and utilizes the contextual information to interpret the words correctly. Representation of the context is achieved by making a unit respond to a series of successively presented words. Interpretation of an input word is achieved by firing a unit which represents the meaning of the word. After learning, one of the units for a word with multiple meanings is correctly fired by using its context information and therefore the network succeeds in giving a correct interpretation of the input word.<
>