Freeze 发表于 2025-4-1 03:39:38
http://reply.papertrans.cn/19/1856/185569/185569_61.png暂停,间歇 发表于 2025-4-1 07:17:04
http://reply.papertrans.cn/19/1856/185569/185569_62.png文艺 发表于 2025-4-1 12:56:53
https://doi.org/10.1007/978-3-030-44762-5nerate rough alignment first, then use bilingual dictionaries to modify the alignment to make it more accurate. We use this alignment as training data and leverage this in training to optimize alignment. We demonstrate that our approach produces better or comparable performance compared to statistical approaches.