Machine translation model training method and device, electronic equipment and storage medium
A technology for machine translation and translation quality, applied in machine learning, computational models, natural language translation, etc., can solve problems such as labor, labor costs, and time-consuming
Pending Publication Date: 2020-10-30
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, in the existing training of machine translation models in the target domain, due to the lack of data in the target domain, more labor costs are required to label bilingual training samples, resulting in time-consuming and laborious training of machine translation models in the target domain. Inefficient training
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0029] 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.
[0030] figure 1 is a schematic diagram according to the first embodiment of the present application; as figure 1 As shown, this embodiment provides a method for training a machine translation model in the target field, which may specifically include the following steps:
[0031] S101. Select a group of samples from the parallel corpus whose translation quality meet...
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
Login to View More Abstract
The invention discloses a machine translation model training method and device, electronic equipment and a storage medium, and relates to the technical field of natural language processing. Accordingto the specific implementation scheme, a group of samples with translation quality meeting a preset requirement and having universal domain characteristics and / or target domain characteristics are selected from a parallel corpus to form a first training sample set; selecting a group of samples which have translation quality meeting preset requirements and do not have universal domain characteristics and target domain characteristics from a parallel corpus to form a second training sample set; and respectively adopting the first training sample set and the second training sample set to sequentially train the encoder of the machine translation model in the target field, the discriminator configured in each encoding layer of the encoder, and the encoder and decoder of the machine translationmodel in the target field. According to the training method, time and labor are saved, and the training efficiency of the machine translation model in the target field can be effectively improved.
Description
technical field [0001] The present application relates to the field of computer technology, in particular to the field of natural language processing technology, and in particular to a training method, device, electronic equipment and storage medium for a machine translation model. Background technique [0002] In Natural Language Processing (NLP), existing machine translation models can be used in all fields to realize the translation of corpus in all fields. Therefore, this machine translation model can be called a machine translation model in the general domain. [0003] In practical applications, when the machine translation model in the general field is trained, bilingual training samples from various fields are collected for training. Moreover, the collected bilingual training samples in various fields are versatile, and are usually training samples that can be recognized in various fields, so as to be applicable to various fields. However, when using a trained machi...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/58G06N20/00
CPCG06F40/58G06N20/00G06F40/45G06F40/44G06N20/20G06F40/47
Inventor 张睿卿张传强刘继强何中军李芝吴华
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD