2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work studies the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and trans-former architectures and proposes token loss dynamic reweighting (TLDR) that applies differentiable weights to individual token losses.
This work studies the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and trans-former architectures and proposes token loss dynamic reweighting (TLDR) that applies differentiable weights to individual token losses.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
