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

Sequence labeling model training method and device and electronic equipment

A technology for sequence labeling and model training, applied in the field of artificial intelligence, which can solve problems such as search or recall matching interference

Pending Publication Date: 2021-03-23
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, with the growth of scale, self-media producers often strive for traffic in order to attract attention, and the problem of redundant titles has gradually emerged, such as "Making a bookshelf from a milk crate is simple and practical!" Several beverages, if you have drunk more than two, it will be unlucky", etc. Redundant titles will interfere with subsequent searches or recall matches. Therefore, it is necessary to extract the core fragments in the titles

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
  • Sequence labeling model training method and device and electronic equipment
  • Sequence labeling model training method and device and electronic equipment
  • Sequence labeling model training method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] 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.

[0029] Such as figure 1 As shown, according to the embodiments of the present application, the present application provides a sequence labeling model training method, the method includes:

[0030] Step S101: Search for target titles matching the search text.

[0031] Various webpages or applications emerge one after another, and a large amount of multimedia informa...

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 sequence labeling model training method and device and electronic equipment, and relates to the technical field of artificial intelligence such as natural language processingand deep learning. The method comprises: searching for a target title matched with a search text, labeling each word in the target title based on the search text to obtain a first label of the targettitle, and training a sequence labeling model by using the training corpus to obtain a target sequence labeling model, the training corpus comprising a target title and a first label of the search text. That is to say, in the training process, a large amount of data does not need to be manually labeled to obtain training corpora for training, and the model training efficiency can be improved.

Description

technical field [0001] The present application relates to artificial intelligence technology fields such as natural language processing and deep learning in computer technology, and in particular to a training method, device and electronic equipment for a sequence labeling model. Background technique [0002] With the development of Internet technology, various applications emerge in endlessly, and a large number of multimedia information such as articles or videos are produced every day. The powerful user generated content (User Generated Content, UGC) generation ability can quickly cover knowledge or entertainment in various fields, etc. need. [0003] However, with the growth of scale, self-media producers often strive for traffic in order to attract attention, and the problem of redundant titles has gradually emerged, such as "Milk crates make bookshelves, simple and practical!", "Online reviews drink once and don't want to drink again Several beverages, if you have had...

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): G06F16/9535G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/9535G06F40/30G06N3/049G06N3/08G06N3/045G06F18/22G06F18/214Y02D10/00
Inventor 宋丹丹姚后清施鹏
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD