Preposition phrase identification method based on multi-model advantage complementation strategy

Abstract

The invention relates to a preposition phrase identification method based on a multi-model advantage complementation strategy. The method includes the following steps of classifying preposition phrases, classifying prepositions according to the characters of contexts, and conducting analysis and summary on the preposition phrases according to the sentence constituents and position characters of the preposition phrases to obtain position characters corresponding to different types; selecting different position character combinations according to different types, adopting a conditional random field model to identify the preposition phrases, and selecting training corpus characters; according to the selected training corpus characters, training multiple preposition phrase identification models, combining the identification results of each preposition in sentences, and obtaining a final result. According to the characters of the prepositions and the prepositional phases, a prepositional phase identification strategy based on multi-model advantage complementation is put forwards; through a 10-fold cross validation method and a contrast experiment, the effectiveness and applicability ofthe method are proved, and the identification effect on the preposition phrases is further improved.

Description

technical field [0001] The invention relates to a natural language processing technology, in particular to a prepositional phrase recognition method based on a multi-model complementary strategy. Background technique [0002] Prepositions belong to function words and are a relatively closed class. A preposition table is listed in "Detailed Explanation of Modern Chinese Grammatical Information Dictionary" edited by Yu Shiwen of Peking University [1], and there are 85 prepositions in the table. A preposition phrase (Preposition Phrase, hereinafter referred to as PP) consists of two parts: the front part is a preposition, and the latter part is a content word or phrase combined with the preposition. According to the composition of PP, the left boundary of PP must be a preposition, so the recognition of prepositional phrases mainly focuses on the determination of the right boundary. The purpose of PP is mainly to make attributives, adverbials, and complements in sentences [2], ...

AI Technical Summary

Problems solved by technology

[0005] In view of the prepositional phrase recognition method based on machine learning in the prior art, the prepositional phrase is not classified according to the context features, resulting in all categories using the same statistical model to identify and other deficiencies. The problem to be solved in the present invention is to provide a method that can further improve Prepositional Phrase Recognition Method Based on Multi-model Advantage Complementary Strategy for Recognition Effect of Prepositional Phrase

Images