CASIA OpenIR

浏览/检索结果: 共5条,第1-5条 帮助

限定条件                
已选(0)清除 条数/页:   排序方式:
E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation 会议论文
Proceedings of the 17th Document Analysis and Recognition (ICDAR 2023), San José, California, USA, August 21-26, 2023
作者:  Ma, Cong;  Zhang, Yaping;  Tu, Mei;  Zhao, Yang;  Zhou, Yu;  Zong, Chengqing
Adobe PDF(1430Kb)  |  收藏  |  浏览/下载:19/5  |  提交时间:2024/06/26
Multi-teacher Knowledge Distillation for End-to-End Text Image Machine Translation 会议论文
Proceedings of the 17th Document Analysis and Recognition (ICDAR 2023), San José, California, USA, August 21-26, 2023
作者:  Ma, Cong;  Zhang, Yaping;  Tu, Mei;  Zhao, Yang;  Zhou, Yu;  Zong, Chengqing
Adobe PDF(1478Kb)  |  收藏  |  浏览/下载:22/10  |  提交时间:2024/06/26
Modal Contrastive Learning Based End-to-End Text Image Machine Translation 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM TASLP), 2023, 卷号: 32, 期号: 32, 页码: 2153-2165
作者:  Ma, Cong;  Han, Xu;  Wu, Linghui;  Zhang, Yaping;  Zhao, Yang;  Zhou, Yu;  Zong, Chengqing
Adobe PDF(6551Kb)  |  收藏  |  浏览/下载:20/9  |  提交时间:2024/06/26
Transformers  Machine translation  Decoding  Semantics  Pipelines  Text recognition  Task analysis  Text image machine translation  contrastive learning  text image recognition  machine translation  
CCIM: Cross-modal Cross-lingual Interactive Image Translation 会议论文
Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore, December 6-10, 2023
作者:  Ma, Cong;  Zhang, Yaping;  Tu, Mei;  Zhao, Yang;  Zhou, Yu;  Zong, Chengqing
Adobe PDF(373Kb)  |  收藏  |  浏览/下载:19/7  |  提交时间:2024/06/26
面向标注数据稀疏场景的任务型对话技术研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学学位评定委员会, 2021
作者:  刘庆斌
Adobe PDF(5059Kb)  |  收藏  |  浏览/下载:193/8  |  提交时间:2022/01/19
自然语言处理  任务型对话系统  标注数据稀疏