Supercharge Your Innovation With Domain-Expert AI Agents!

Description text generation model training method and device

A technology for generating models and texts, which can be used in unstructured text data retrieval, text database clustering/classification, special data processing applications, etc., and can solve problems such as labor-intensive

Active Publication Date: 2019-10-22
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF12 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method requires a lot of expert knowledge to complete the configuration of templates and logic conditions, which is labor-intensive

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
  • Description text generation model training method and device
  • Description text generation model training method and device
  • Description text generation model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0106]When determining the data sequence corresponding to the reference description text based on the matching and alignment results, each data record that is matched and aligned can be directly used as the data sequence corresponding to the reference description text. However, there may be such a situation in this way. Although the sentence contains entities and entity values, the relationship between them expressed is not consistent with the relationship labels in the data records. Therefore, a preferred embodiment is provided here: input the matched and aligned sentences into the relation extraction model obtained in advance training respectively, and obtain the relation labels corresponding to each sentence; if the relation labels corresponding to the sentences are aligned with the sentence If the tags are consistent, the data record corresponding to the sentence is retained; otherwise, the data record corresponding to the sentence is modified using the relation label gener...

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 provides a description text generation model training method and device, and the method comprises the steps: obtaining training data which comprises structural data and reference description texts corresponding to each group of structural data; preprocessing the training data to obtain a data sequence corresponding to the reference description text; utilizing the structured data anda data sequence corresponding to the reference description text to train a first sequence to a sequence seq2seq model; training a second seq2seq model by utilizing a first data sequence output by thefirst seq2seq model and referring to the description text and a dynamic programming annotation result; and obtaining a description text generation model by using the trained first seq2seq model and second seq2seq model, the description text generation model being used for generating a description text for the input structured data.

Description

【Technical field】 [0001] The present invention relates to the field of computer application technology, in particular to a training method, device, equipment and computer storage medium for describing a text generation model. 【Background technique】 [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Reading and understanding structured data such as tabular data is usually unfriendly and boring, and it usually takes a lot of time for someone with a professional knowledge background to be able to understand the meaning expressed by the data. However, most fields collect and store structured data, such as weather data, financial data, traffic data, and so on. In order to lower the threshold for readers and save reading time, it is necessary to convert structured data into descriptive text, so that...

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): G06F17/27G06F16/35
CPCG06F16/35G06F40/289G06F40/30
Inventor 李法远彭卫华罗雨
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com