JavaShuo
欄目
標籤
論文閱讀 Training Neural Machine Translation To Apply Terminology Constraints
時間 2021-01-02
標籤
論文
简体版
原文
原文鏈接
一. 該方法是在模型訓練層面解決術語注入的問題。 二. 訓練階段主要是改變數據的處理方式: 1. 原始數據層面(增加註釋,0無關,1源語術語,2目標語言術語) 2.bpe層面 將原始數據的註釋推廣到bpe切分後的token上,eg:如果Stellvertreter_2切分成了a、b,則a_2,b_2。 3.embedding層面 將註釋向量和詞向量進行拼接。 4. 術語覆蓋度問題 爲了保證沒有包
>>阅读原文<<
相關文章
1.
論文閱讀——Robust Unsupervised Neural Machine Translation with Adversarial Training
2.
論文閱讀《NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE》
3.
論文閱讀:《Neural Machine Translation by Jointly Learning to Align and Translate》
4.
【論文閱讀】Neural Machine Translation By Jointly Learning To Align and Translate
5.
【論文閱讀】Neural Machine Translation by Jointly Learning to Align and Translate
6.
Neural machine translation by jointly learning to align and translate論文閱讀筆記
7.
論文閱讀:Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
8.
論文閱讀:ByteNet, Neural Machine Translation in Linear Time
9.
[論文閱讀筆記] Massive Exploration of Neural Machine Translation Architectures
10.
論文閱讀——Unsupervised Neural Machine Translation with Indirect Supervision
更多相關文章...
•
RSS 閱讀器
-
RSS 教程
•
Docker Machine
-
Docker教程
•
JDK13 GA發佈:5大特性解讀
•
Scala 中文亂碼解決
相關標籤/搜索
論文閱讀
CV論文閱讀
terminology
constraints
machine
translation
外文閱讀
neural
training
論文解讀
Thymeleaf 教程
PHP教程
Redis教程
文件系統
0
分享到微博
分享到微信
分享到QQ
每日一句
每一个你不满意的现在,都有一个你没有努力的曾经。
最新文章
1.
shell編譯問題
2.
mipsel 編譯問題
3.
添加xml
4.
直方圖均衡化
5.
FL Studio鋼琴卷軸之畫筆工具
6.
中小企業爲什麼要用CRM系統
7.
Github | MelGAN 超快音頻合成源碼開源
8.
VUE生產環境打包build
9.
RVAS(rare variant association study)知識
10.
不看後悔系列!DTS 控制檯入門一本通(附網盤鏈接)
本站公眾號
歡迎關注本站公眾號,獲取更多信息
相關文章
1.
論文閱讀——Robust Unsupervised Neural Machine Translation with Adversarial Training
2.
論文閱讀《NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE》
3.
論文閱讀:《Neural Machine Translation by Jointly Learning to Align and Translate》
4.
【論文閱讀】Neural Machine Translation By Jointly Learning To Align and Translate
5.
【論文閱讀】Neural Machine Translation by Jointly Learning to Align and Translate
6.
Neural machine translation by jointly learning to align and translate論文閱讀筆記
7.
論文閱讀:Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
8.
論文閱讀:ByteNet, Neural Machine Translation in Linear Time
9.
[論文閱讀筆記] Massive Exploration of Neural Machine Translation Architectures
10.
論文閱讀——Unsupervised Neural Machine Translation with Indirect Supervision
>>更多相關文章<<