To search, Click below search items.


All Published Papers Search Service


A Method for Retrieving and Building Structure of NLP Knowledge


Elmarhmoy Ghada, El-Sayed Atlam, Masao Fuketa, Kazuhiro Morita, Jun-ichi Aoe


Vol. 6  No. 4  pp. 42-47


Knowledge-based natural language understanding requires the representation of various types of knowledge like linguistic knowledge, conceptual knowledge or knowledge about real world objects. This paper proposes a method of a retrieving and building structure of natural language processing knowledge. We classify all surface case patterns in advance and then consider the typical meaning of noun which has one of these patterns. We present also an efficient data structure by introducing a trie that can define the linkage among leaves. The linkage enables us to share the basic words required for multi-attribute relations. By using this linkage, and a high frequent access between verbs with noun, we could extract an automatic generation of hierarchical relationships. This new method applied to the data extracted from a large tagged corpus (Pan Treebank). From relationships for 11,000 verbs and nouns, it is verified that the presented method is simulated the number and frequent of typical verb, and made a hierarchy group of its noun, and net of linkage group with this high frequent.


Natural Language Processing, trie structure, Hierarchy.