Unlock instant, AI-driven research and patent intelligence for your innovation.

Text processing method and device based on natural language and knowledge graph

A knowledge graph and natural language technology, applied in the field of text processing methods and devices based on natural language and knowledge graphs, can solve the problems of poor text processing accuracy and poor semantic representation accuracy, and achieve the effect of improving accuracy

Active Publication Date: 2020-01-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the accuracy of the semantic representation learned based on the above text processing method is poor, resulting in poor accuracy of text processing when the above semantic representation is used for text processing.

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
  • Text processing method and device based on natural language and knowledge graph
  • Text processing method and device based on natural language and knowledge graph
  • Text processing method and device based on natural language and knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0039] Generally speaking, knowledge graph and natural language processing are two independent fields. The two fields each develop independent representation learning systems, and the representation learning technologies in each field follow different modeling methods and optimization goals, and there is no cross-fusion. Knowledge graph representation learning usual...

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 text processing method and device based on a natural language and a knowledge graph, and relates to the technical field of artificial intelligence. According to the specificimplementation scheme, an electronic device uses semantic representation obtained by a joint learning model, the joint learning model is obtained by combining knowledge graph representation learning and natural language representation learning and combines knowledge graph learning representation and natural language learning representation; compared with semantic representation of learning a prediction object only through knowledge graph representation learning or natural language representation learning, the joint learning model considers more and more comprehensive factors, and therefore theaccuracy of semantic representation can be improved, and the accuracy of text processing is improved.

Description

technical field [0001] The embodiments of the present disclosure relate to the technical field of artificial intelligence (Artificial Intelligence, AI), and in particular, to a text processing method and apparatus based on natural language and knowledge graphs. Background technique [0002] At present, in order to obtain valuable information from massive data, knowledge graph (KG) emerges as the times require. At the same time, as a tool and carrier for people to communicate and think, the representation of characters and words in natural language is the basic processing object of language processing artificial intelligence tasks based on deep learning. [0003] Usually, knowledge graph and natural language are two independent fields, both of which have independently developed representation learning technology systems. Among them, knowledge graph representation learning is usually in the form of vector space operations, and the knowledge graph contains Model the co-occur...

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
IPC IPC(8): G06F16/36G06F40/295
CPCG06F16/367G06F16/9024G06N3/04G06N3/08G06N5/02
Inventor 王海峰姜文斌吕雅娟朱勇吴华
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD