From cde9adb6d524e7c4520337d2c72fbb40e8d58664 Mon Sep 17 00:00:00 2001 From: "A. Unique TensorFlower" Date: Tue, 6 Sep 2016 15:15:42 -0800 Subject: [PATCH] All other tensors from this list would be ignored, and instead the previous output of the decoder would be used. Change: 132374855 --- tensorflow/g3doc/tutorials/seq2seq/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tensorflow/g3doc/tutorials/seq2seq/index.md b/tensorflow/g3doc/tutorials/seq2seq/index.md index c1673f474d5..10f39553fd0 100644 --- a/tensorflow/g3doc/tutorials/seq2seq/index.md +++ b/tensorflow/g3doc/tutorials/seq2seq/index.md @@ -126,7 +126,7 @@ In the above invocation, we set `feed_previous` to False. This means that the decoder will use `decoder_inputs` tensors as provided. If we set `feed_previous` to True, the decoder would only use the first element of `decoder_inputs`. All other tensors from this list would be ignored, and instead the previous -output of the encoder would be used. This is used for decoding translations +output of the decoder would be used. This is used for decoding translations in our translation model, but it can also be used during training, to make the model more robust to its own mistakes, similar to [Bengio et al., 2015](http://arxiv.org/abs/1506.03099)