首页> 外国专利> Transformer Translation System for Deep Learning Using Triple Sentence Pair

Transformer Translation System for Deep Learning Using Triple Sentence Pair

机译:使用三重句对深入学习变压器翻译系统

摘要

The deep learning transformer translation system using the triple corpus creates proofreading data through rough translation, reinforcement learning using deep learning functions, and proofreading translation, and emotions, nuances, and moods in literature, webtoons, and video subtitles that can be distributed and exported commercially overseas. , slang, tone, author''s intentions, context, etc. are economically reflected, and accordingly, it has the effect of improving the translation level of the level of actual reading and consumption, rather than the level of conveying meaning to the reader. The deep learning transformer translation system using the triple corpus can produce the final version that can be distributed unmanned without restrictions 24 hours a day, and through the process of achieving the singularity (meaning: artificial intelligence final evolution, completed), it is an essential step to the completion of the final translation. The need and frequency of phosphorus calibration and inspection are relatively reduced or unnecessary, thereby improving economic efficiency.
机译:使用三重语料库的深度学习变压器翻译系统通过粗略的翻译,使用深度学习功能,以及校对的翻译,以及文学,Webtoons和视频字幕的校对翻译和情感,校对的翻译和情绪化的校对的翻译和情绪。海外。 ,俚语,语气,作者的意图,上下文等在经济上反映,因此,它具有改善实际读取和消费水平的翻译水平,而不是对读者的传送意义的水平。使用三重语料库的深层学习变压器翻译系统可以生产最终版本,可以在每天24小时内没有限制分发无人,并且通过实现奇点的过程(意思:完成的人工智能最终进化,完成),这是一个必不可少的步骤完成最终翻译。磷校准和检查的需求和频率相对减少或不必要,从而提高了经济效率。

著录项

  • 公开/公告号KR102306344B1

    专利类型

  • 公开/公告日2021-09-28

    原文格式PDF

  • 申请/专利权人 남지원;

    申请/专利号KR20210034738

  • 发明设计人 남지원;

    申请日2021-03-17

  • 分类号G06F40/51;G06F9/451;G06N3/08;

  • 国家 KR

  • 入库时间 2022-08-24 21:19:03

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号