Verb metaphor recognition method based on multi-verb extraction and thinking chain prompt

By using multi-verb extraction and thinking chain prompting methods in the Chinese context, and combining MIP and SPV theories to generate metaphorical interpretation information, the problem of insufficient accuracy and interpretability of verb metaphor recognition in the existing technology is solved, and a more efficient metaphor recognition effect is achieved.

CN119646226AActive Publication Date: 2025-03-18DALIAN UNIV OF TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202411861672.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-17
Publication Date
2025-03-18
Estimated Expiration
2044-12-17

AI Technical Summary

Technical Problem

The prior art is difficult to efficiently identify and interpret verb metaphors in the Chinese context, especially when multiple verbs are included in the sentence, the recognition accuracy and interpretability are insufficient.

Method used

Using a method based on multi-verb extraction and thinking chain prompt, all verbs in the sentence are extracted through word segmentation tools, and metaphorical interpretation information is generated by combining MIP and SPV theories and thinking chain prompts, and input models for encoding to improve recognition accuracy.

Benefits of technology

It significantly improves the accuracy and interpretability of verb metaphor recognition, and can capture the metaphorical characteristics in multi-verb scenes more comprehensively and efficiently.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A verb metaphor recognition method based on multi-verb extraction and thinking chain prompt belongs to the field of natural language processing in deep learning, is used for metaphor recognition of Chinese sentences, and has the key points that verbs in texts in a data set are extracted; performing thinking chain prompt on the large model to obtain a prompt result whether the verb is a metaphor; splicing a sentence where the verb is located in the text with the verb, and encoding to obtain a sentence feature vector; encoding the prompt result into a thinking chain feature vector; splicing the sentence feature vector and the thinking chain feature vector according to a certain weight ratio to obtain a spliced feature vector; and inputting the spliced feature vector into a classification model for metaphor judgment to obtain a judgment result of whether the sentence contains the metaphor, and the method can significantly improve the accuracy and interpretability of metaphor recognition.
Need to check novelty before this filing date? Find Prior Art