Hello, I have a question in the paper. In the Input Context in the decoder of Fig 3, if a character line is entered during training, is this part removed during testing?

[Zoeun]

[baudm]

During training, all input tokens are used in the input context in order to take advantage of the parallel processing of Transformers.

For testing, only [B] (the beginning-of-sequence token) is used as input context initially.