微信服务号

微信订阅号

2025-4-9- 8
Home > Archive>Volume 34, Issue 11, 2023 >5113-5125. DOI:10.13328/j.cnki.jos.006689
PDF HTML XML Export Cite reminder
Low-resource Neural Machine Translation with Multi-strategy Prototype Generation
Author:
Affiliation:

Clc Number:

TP18

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related
    • |
  • Cited by
    • | |
  • Comments
    Abstract:

    In rich-resource scenarios, using similarity translation as the target prototype sequence can improve the performance of neural machine translation. However, in low-resource scenarios, due to the lack of parallel corpus resources, the prototype sequence cannot be matched, or the sequence quality is poor. To address this problem, this study proposes a low-resource neural machine translation approach with multi-strategy prototype generation, and the approach includes two phases. (1) Keyword matching and distributed representation matching are combined to retrieve prototype sequences, and the pseudo prototype generation approach is leveraged to generate available prototype sequences during retrieval failures. (2) The conventional encoder-decoder framework is improved for the effective employment of prototype sequences. The encoder side utilizes additional encoders to receive prototype sequences. The decoder side, while employing a gating mechanism to control information flow, adopts improved loss functions to reduce the negative impact of low-quality prototype sequences on the model. The experimental results on multiple datasets show that the proposed method can effectively improve the translation performance compared with the baseline models.

    Reference
    Related
    Cited by
Get Citation

于志强,余正涛,黄于欣,郭军军,线岩团.基于多策略原型生成的低资源神经机器翻译.软件学报,2023,34(11):5113-5125

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:April 14,2021
  • Revised:June 28,2021
  • Online: April 27,2023
  • Published: November 06,2023
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063