mRASP2
mRASP2 copied to clipboard
PANXiao1994
Hi, In **mRASP2**, inappropriate dependency versioning constraints can cause risks. Below are the dependencies and version constraints that the project is using ``` subword-nmt sacrebleu sacremoses kytea six ``` The...
 Hello, our team recognizes your work very much, but there are some problems during the replication: download After changing the domain name in the. sh file, a 404 error...
On WMT16 en->ro benchmark, the reported results on this website (28.7) is quite different from that reported in your paper (38.0). Is it possible for you to release your bpe...
it seems that there is no introduction about how to fine-tune the pre-trained model. Could you get me some instructions?
Hi Xiao, I have a question about the swap_sample function in label_smoothed_cross_entropy_with_contrastive.py https://github.com/PANXiao1994/mRASP2/blob/d4d627b8442af062a5b6607a459fe53c6b516695/mcolt/criterions/label_smoothed_cross_entropy_with_contrastive.py#L39 Here, after swaping the sample, src_tokens are the same as the original target tokens. However, the padding...
您好，想请教一下论文图2的可视化技术，使用了什么算法将词嵌入转化为坐标的点，并用夹角来描述相似度呀？谢谢！ 
Hi there, I have been trying to use the mRASP2 model for evaluation and have run into a couple of issues. 1. The sample yaml file for evaluation has the...
您好，请问您在 wmt17的 zh-en 以及 en-zh 两个方向上设置的学习率和optimizer 的具体参数是多少呢？是仅仅用了 wmt17的 中英平行语料进行微调吗？wmt17的中英训练数一共多少 sample呢？大概是训练了多少个 epoch 收敛的？ 期待您的答复！
