Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Legal text representation method based on decoupling legal elements

A text representation and legal technology, applied in natural language processing, legal field based on decoupling model, can solve problems such as less consideration of legal documents, text representation is difficult to directly apply to other tasks, etc., to achieve strong versatility

Active Publication Date: 2021-06-11
EAST CHINA NORMAL UNIV
View PDF13 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing work rarely considers the characteristics of legal documents on legal elements, and most of the model training is closely combined with downstream tasks. The text representation obtained by a task training is often difficult to directly apply to other tasks.

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
  • Legal text representation method based on decoupling legal elements
  • Legal text representation method based on decoupling legal elements
  • Legal text representation method based on decoupling legal elements

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In conjunction with the following specific embodiments and accompanying drawings, the invention will be further described in detail. The process, conditions, experimental methods, etc. for implementing the present invention, except for the content specifically mentioned below, are common knowledge and common knowledge in this field, and the present invention has no special limitation content.

[0045] See attached figure 1 , the present invention performs legal text representation learning based on decoupling legal elements according to the following steps:

[0046] Step 1: Define web crawlers to crawl legal ruling documents, and define relevant legal elements according to the types of legal ruling documents to be processed and relevant laws and regulations. Legal elements are domain knowledge with a finer granularity than laws and regulations. For example, in loan cases, "the attributes of the borrower and lender", "guarantee type" and "loan purpose" are all key facto...

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 legal text representation method based on decoupling legal elements, which comprises: definition and labeling of the legal elements, data construction, model training, specific application of downstream tasks and the like, and combines field knowledge of the legal elements with a deep learning model. For a text containing a certain legal element, a triple is constructed by means of a positive sample containing the legal element and a negative sample not containing the legal element, and vector representation of the legal text about the legal element is learned based on triplet loss. For a plurality of legal elements, a triple is constructed for each legal element and a corresponding model is trained, and model training among different legal elements is mutually independent and does not influence each other. According to the method, the nuisance among the legal elements can be well captured, meanwhile, the influence of other irrelevant information is reduced, and a new solution is provided for text representation in the legal field.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a decoupling model-based text representation method in the legal field. Background technique [0002] In recent years, with the publication of a large number of judgment documents on the Internet, researchers have provided a large amount of data, and more and more studies have begun to focus on tasks in the judicial field, such as similar case recommendation and crime prediction. These tasks all play an important role in the judicial assistance system. On the one hand, the judicial assistance system can provide low-cost but high-quality legal consulting services for those who lack legal knowledge and do not understand complex legal processes; on the other hand, it can provide legal workers (such as lawyers and judges) with a series of references to increase their productivity. The first step of the tasks in the above-mentioned judicial assistance systems is ...

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): G06Q50/18G06F40/284G06F40/211G06N3/04G06N3/08
CPCG06Q50/18G06F40/284G06F40/211G06N3/04G06N3/08Y02D10/00
Inventor 缪影芝宗为娴周昉金澈清钱卫宁
Owner EAST CHINA NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com