Verb-verb semantic relationship recognition method and device

• Main Authors: WANG MIN, WANG SHUNLI, LI SHENGNAN, XING HONGWEN, CHEN ZHICHAO, LUAN YINGWEI, LIU KUI
• Format: Patent
• Language: Chinese; English
• Published: 23.01.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a verb-verb semantic relationship recognition method and device, which are used in the technical field of neural networks, and the method comprises the steps: recognizing a vector representation and a semantic role tag of each word of a statement; encoding the semantic role tag of each word to obtain a vector representation corresponding to the semantic role tag of each word; splicing the vector representation of each character and the vector representation corresponding to the semantic role tag of each character to obtain a spliced vector of each character; and inputting the splicing vector of each character of the to-be-recognized statement into a decoder for decoding to obtain a prediction label corresponding to each character of the to-be-recognized statement, so that the relationship between various verbs, the specific roles of the verbs in the structural relationship and the applicant corresponding to each verb can be recognized, and the verbs can be recognized. Therefore, the sem