A Fully Differentiable Beam Search Decoder
International Conference on Machine Learning, pp. 1341-1350, 2019.
We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g. acoustic and language models). It can be used when target sequences are not aligned to input sequences ...More
PPT (Upload PPT)