Semantic role labeling method based on synergetic neural network

Abstract

The invention discloses a semantic role labeling method based on a synergetic neural network, and relates to the fields of semantic role labeling, mode identification and synergetic neural networks, in particular to a method for introducing the principle of the synergetic neural network into shallow semantic analysis. The semantic role labeling method comprises the following steps: extracting characteristics from training language material and testing language material and constructing corresponding semantic characteristic vectors; performing kernel transformation on the semantic characteristic vectors and constructing a prototype pattern and a mode to be tested on the basis; constructing an order parameter and calculating a plurality of candidate roles for each dependent component; constructing a predicate base and combining the candidate roles of all the dependent components corresponding each predicate to get role chains of all the predicates; and optimizing a network parameter, performing dynamic evolution on the synergetic neural network to get an optimal role chain, and outputting the labeling mode. The principle of the synergetic neural network is firstly introduced into the semantic role labeling, and the method can be widely applicable to various natural language processing tasks. The semantic role labeling method has better application prospects and application value.

Description

technical field [0001] The invention relates to the fields of semantic role labeling, pattern recognition and collaborative neural network, relates to a method for introducing the principle of collaborative neural network into shallow semantic analysis, and in particular to a semantic role labeling method based on the collaborative neural network. Background technique [0002] As a main research direction of natural language processing, semantic analysis can transform natural language into a formal language that computers can understand, so as to achieve mutual understanding between humans and computers. Correct semantic analysis of sentences has always been the main goal pursued by scholars engaged in natural language understanding research. However, limited by the complexity of semantics, current semantic analysis mainly focuses on role labeling and other aspects. Semantic role labeling does not carry out detailed semantic analysis on the entire sentence, it only labels t...

AI Technical Summary

Problems solved by technology

But there will be a label bias problem that will affect the final performance

Images