Non-autoregressive Mongolian-Chinese machine translation method based on round-robin decoding and vocabulary attention

A technology of machine translation and regression method, applied in the field of machine translation, to achieve the effect of reducing the possibility of repeated generation, reducing time, and reducing repeated generation

Pending Publication Date: 2021-02-26
INNER MONGOLIA UNIV OF TECH
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0024] Moreover, existing autoregressive and non-autoregressive models are usually trained using cross-entropy loss. Cross-entropy is a strict loss function that predicts out-of-position words are penalized, even for output sequences with small edit distances.

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
  • Non-autoregressive Mongolian-Chinese machine translation method based on round-robin decoding and vocabulary attention
  • Non-autoregressive Mongolian-Chinese machine translation method based on round-robin decoding and vocabulary attention
  • Non-autoregressive Mongolian-Chinese machine translation method based on round-robin decoding and vocabulary attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0061] refer to image 3 , the present invention is a non-autoregressive Mongolian-Chinese machine translation method based on look-around decoding and vocabulary attention, based on the translation model of encoder-target length predictor-decoder, using an improved non-autoregressive method to improve Mongolian-Chinese neural machine translation speed and parallelism, and uses aligned cross-entropy as a loss function during training. The improved non-autoregressive method is as follows: first use position embedding when decoding, and then decode through look-around decoding and dynamic two-way decoding, and run each layer of the decoder (there are six layers in the decoder, respectively: Masked Self- Attention, Multi-headAttention, Feed forward and three-layer Add&Norm), all use vocabulary attention. Through the above method, in the Mongolian...

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 non-autoregressive Mongolian-Chinese machine translation method based on round-robin decoding and vocabulary attention, and the possibility of repeated generation is reduced by using round-robin generation; according to the method, vocabulary attention is used, each layer of a decoder is operated, each position pays attention to the whole word list, characters which are possibly generated are obtained, through the vocabulary attention, the decoder can enable the characters which are expected to be generated at all the positions to be interacted, and therefore the possibility of repeated generation is reduced, and meanwhile extra parameters do not need to be introduced; according to the method, the aligned cross entropy is used as a loss function of the non-autoregressive translation model, so that the problem that Mongolian word orders are difficult to model due to lack of autoregressive factors in the non-autoregressive translation model is solved; and duringdecoding, dynamic bidirectional decoding is adopted, so that a sentence-level better sampling result is obtained. According to the method, the decoding speed is increased in the Mongolian-Chinese translation process, and meanwhile the translation quality is improved.

Description

technical field [0001] The invention belongs to the technical field of machine translation, in particular to a non-autoregressive Mongolian-Chinese machine translation method based on look-around decoding and vocabulary attention. Background technique [0002] As one of the fundamental components of artificial intelligence, machine translation provides a method for solving language translation problems. Machine translation is the process of using computers to realize rapid conversion between two natural languages. The development of machine translation technology has been closely related to computer technology, information theory, linguistics The development of other disciplines closely followed. From the 1949 translation memorandum to the present, during this period, machine translation has gone through many different stages of development, and many methods have emerged. To sum up, there are three main categories, which are rule-based methods at first, and then develop into...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/58G06F40/126G06N3/04G06N3/08
CPCG06F40/58G06F40/126G06N3/08G06N3/045
Inventor 苏依拉王涵张妍彤仁庆道尔吉石宝
Owner INNER MONGOLIA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products