Matching viewpoint mining related method, device and equipment

An opinion mining and opinion technology, which is applied in text database query, instrumentation, unstructured text data retrieval, etc., can solve problems such as inability to mine debate texts to match opinions, and achieve the effect of improving mining accuracy

Pending Publication Date: 2022-04-12
ALIBABA GRP HLDG LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a matching viewpoint mining method to solve the problem that existing technologies cannot mine one-to-one corresponding matching viewpoints in debate texts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Matching viewpoint mining related method, device and equipment
  • Matching viewpoint mining related method, device and equipment
  • Matching viewpoint mining related method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0051] Please refer to figure 1 , which is a schematic flowchart of an embodiment of the matching viewpoint mining method of the present application. The subject of execution of the method includes, but is not limited to, the server, and may also be any device capable of implementing the method. In this embodiment, the method may include the following steps:

[0052] Step S101: Acquiring the first text and the second text including matching viewpoints.

[0053] The first text and the second text constitute a debate text, and the method can perform matching opinion mining on a longer debate text.

[0054] In an example, the method is applied in the field of debate, the first text may be a positive debate text, and the second text may be a negative debate text. By means of the method, pros and cons can be mined from pros and cons debate texts.

[0055] In another example, the method is applied in the field of intelligent justice, the first text may be a text provided by the ...

no. 2 example

[0084] In the foregoing embodiments, a matching viewpoint mining method is provided, and correspondingly, the present application also provides a matching viewpoint mining device. The device corresponds to the embodiment of the above-mentioned method. The parts in this embodiment that are the same as those in the first embodiment will not be described again, please refer to the corresponding parts in the first embodiment.

[0085] A matching viewpoint mining device provided by the present application includes:

[0086] a debate text acquisition unit, configured to acquire a first text and a second text including matching viewpoints, the first text and the second text include sentences;

[0087] The shared sentence vector determination unit is used to determine the shared sentence vector of the sentence according to the word vector in the sentence by matching the shared sentence vector in the viewpoint recognition model;

[0088] The matching point of view determination unit ...

no. 3 example

[0104] The present application also provides an electronic device. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to part of the description of the method embodiment. The device embodiments described below are illustrative only.

[0105] An electronic device in this embodiment, the electronic device includes: a processor and a memory; the memory is used to store a program for realizing the method for matching viewpoint mining, and after the device is powered on and runs the program of the method through the processor, the following steps are executed: Described step: obtain the first text and the second text that comprise matching viewpoint, described first text and the second text comprise sentence; By matching the shared sentence vector determination module in the viewpoint recognition model, according to the word vector in the sentence, determine sentence The shared senten...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a matching viewpoint mining method and device. The method comprises the steps that a first text and a second text are obtained, and the first text and the second text comprise sentences; determining shared sentence vectors of the sentences according to word vectors in the sentences through a shared sentence vector determination module in the matched viewpoint recognition model; judging whether the sentence is an argument or not according to the shared sentence vector by matching an argument classifier in the viewpoint recognition model; and judging whether the first text sentence and the second text sentence are matched viewpoints or not according to the shared sentence vector through a matched viewpoint classifier in the matched viewpoint recognition model. By adopting the processing mode, the multitask training model is combined with two sub-tasks, namely a debate mining sub-task and a debate pairing sub-task, so that better shared sentence representation is learned, and then one-to-one corresponding matching viewpoints in a debate text are mined; therefore, the matching viewpoint mining accuracy can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of debate mining, and specifically relates to a matching viewpoint mining method and device, a matching viewpoint recognition model building method and device, a debate robot system, and electronic equipment. Background technique [0002] Argumentation mining (Argumentation Mining) is an important task in computational argumentation. Its main goal is to automatically extract arguments (Argument) from texts in order to provide structured data for argumentative and inference engine computational models. Currently, most of the existing argumentative mining tasks perform argumentative mining from a single passage, such as extracting arguments from legal documents, dissertations, etc. Furthermore, existing multi-text-based argumentative mining is limited to online discussions or debates in forums, where arguments are extracted from a large number of articles in online forums. [0003] In the process of...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/279G06F40/284G06F16/33G06F16/35
Inventor 程丽颖邴立东司罗陆巍
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap