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

Text processing and model training method and device, storage medium and electronic equipment

A text processing and text technology, applied in the field of machine translation, can solve problems such as the decline in the translation effect of the translation model and the negative impact on the translation effect, and achieve the effect of improving domain adaptability and improving the translation effect

Pending Publication Date: 2020-10-16
BEIJING DIDI INFINITY TECH & DEV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, adding domain-specific corpus to the training set will have a negative impact on the translation effect of the original domain, making the translation effect of the translation model on the original domain lower.

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 and model training method and device, storage medium and electronic equipment
  • Text processing and model training method and device, storage medium and electronic equipment
  • Text processing and model training method and device, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention is described below based on examples, but the present invention is not limited to these examples. In the following detailed description of the invention, some specific details are set forth in detail. The present invention can be fully understood by those skilled in the art without the description of these detailed parts. In order not to obscure the essence of the present invention, well-known methods, procedures, procedures, components and circuits have not been described in detail.

[0056] Additionally, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0057]Meanwhile, it should be understood that in the following description, "circuit" refers to a conductive loop formed by at least one element or sub-circuit through electrical connection or electromagnetic connection. When an element or circuit is said to be "connected to" another elemen...

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 and model training method and device, a storage medium and electronic equipment. The method comprises the steps of detecting each word in a word sequence of ato-be-processed text word sequence according to a public word list and a private word list to obtain a corpus type of the to-be-processed text, determining a weight coefficient of each word in the word sequence according to the corpus type, and obtaining a target text through a pre-trained translation model according to the weight coefficient and an embedded vector of the word sequence. Therefore, under the condition that the translation effect of the text processing model on the original field is not changed, the translation effect on the specific field can be improved, and the field adaptability of the text processing model is improved.

Description

technical field [0001] The present invention relates to the technical field of machine translation, in particular to a text processing and model training method, device, storage medium and electronic equipment. Background technique [0002] Neural network machine translation technology is a technology that uses deep learning methods such as neural networks to translate a natural language (source language) into another language (target language). In practical applications, the text has strong domain characteristics, and the translation results of the same word in different domains will be very different, or even completely different. If the characteristics of words in different fields cannot be well adapted, the translation effect will often fail to meet the expected needs. [0003] The existing technology usually adopts the method of adding specially collected aligned corpus of new domains to the original training set, and then retraining the original translation model with...

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): G06F40/58G06F40/44
CPCG06F40/58G06F40/44
Inventor 魏文扬陈坦访王伟玮李奘
Owner BEIJING DIDI INFINITY TECH & DEV