Description mining system and method based on multi-task sparse shared learning

Abstract

The invention provides a discussion mining system and method based on multi-task sparse shared learning, and the system comprises an encoder module which is used for learning context information through employing a bidirectional long-short-term memory neural network; a double-path attention coding module used for carrying out feature extraction on word vectors by using self-attention and external attention in parallel to obtain word semantic attention degrees from different angles and strengthening relation modeling between words; a sparse shared learning module used for carrying out multi-task learning on the encoding module for obtaining the sentence vector, generating a task-specific sparse parameter matrix for different tasks so as to solve the negative migration influence of multi-task learning, and obtaining sentence-level encoding representation; and a multi-task label output module used for completing classification result prediction of different tasks by using a task-specific classifier. A sparse shared structure of a plurality of tasks can be automatically learned, and the specific sub-networks of the respective tasks are utilized to perform joint training, so that the negative migration phenomenon of multi-task learning is effectively avoided.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to an argument mining system and method based on multi-task sparse shared learning. It can automatically learn the sparse shared structure of multiple tasks, and use the respective task-specific sub-networks for joint training, effectively avoiding the negative transfer phenomenon of multi-task learning. Background technique [0002] Argumentative mining is a research field aimed at extracting arguments from unstructured texts and judging their types and logical relationships. The ultimate goal is to transform unstructured text data into structured data that can be processed by computers. Argumentative mining tasks can generally be divided into the following four subtasks: (1) Extract argumentative text fragments or sentences from the input text, called argument parts. (2) Classify the extracted argument components, generally these units can be divid...

AI Technical Summary

Problems solved by technology

However, multi-task learning does not always bring benefits. Sometimes joint learning of multiple tasks will bring performance loss to one of the tasks. When the correlation between tasks is relatively weak, negative transfer phenomenon is prone to occur.

Images