Xiaodong Gu

Results 3 issues of Xiaodong Gu

As beam search is widely used in machine translation, could you support beam search sampling and evaluate the model?

I use the latest version and check the similarity part of the model, i.e., qa_model = merge([question_output, answer_output], mode=similarity, output_shape=lambda x: x[:-1],name='similarity') When I invoke qa_model.summary(), here is the screen...

what does the argument `num_atoms` mean in the code? `atom` is not shown in the paper.