RESOLUTION OF ANAFORA BASED ON DEPTH ANALYSIS TECHNOLOGY

摘要

1. A method for creating syntactic-semantic structures of sentences of a natural language in automatic word processing systems, a method including: generating, by a computing device processor, at least one syntax tree for each sentence of a natural language, including a plurality of syntactic nodes and a plurality of tree syntactic connections; the generation, by means of the processor of the computing device, of at least one semantic structure corresponding to at least e, one syntax tree, where at least one semantic structure includes many semantic nodes corresponding to many syntax nodes, and many tree semantic links corresponding to many tree syntax links; if at least one syntax tree includes at least at least two different syntactic nodes corresponding to one entity, then the connection of semantic nodes corresponding to these syntactic nodes with at least one non-wood communication ; and performing, by the processor of the computing device, further processing of the text using the resulting semantic structure containing one or more non-wood links. 2. The method of claim 1, wherein joining the semantic nodes with at least one non-wood communication includes: generating a plurality of possible non-wood communication between the syntax nodes; calculating an estimate for each possible non-wood communication; and the selection of possible non-timber links with the highest score. 3. The method of claim 2, wherein calculating the score for each possible