Association-based natural language processing with neural networks
Kazuhiro Kimura, Suzuoka Takashi, Amano Sin-ya · 1992
This paper describes a natural language processing system reinforced by the use of association of words and concepts, implemented as a neural network. Combining an associative network with a conventional system contributes to semantic disambiguation in the process of interpretation. The model is employed within a kana-kanji conversion system and the advantages over conventional ones are shown.