Association-Based Natural Language Processing with Neural Networks

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.

• Type: Conference
• Year: 1992
• Where: ACL
• Authors: Kazuhiro Kimura, Takashi Suzuoka, Shin'ya Amano
• Keywords: ACL 1992, ACL 2007, Associative Network, Natural Language Processing, Semantic Disambiguation