Text summarization results. Shown are ROUGE F-{1,2,L} scores on the test split for the CNN / Daily Mail and the Science Daily datasets. Some settings are different from ours: lines 8–9 show results when training and testing on an anonymized data set, and lines 12–14 use reinforcement learning. The ROUGE scores have a 95% confidence interval ranging within ±0.25 points absolute. For lines 2 and 7, the maximum decoder steps during testing is 100. In lines 15–18, L/dR stands for LEAD/decRUM. Replacing ReLU with tanh or removing the update gate in decRUM line 17 yields a drop in ROUGE of 0.01/0.09/0.25 and 0.36/0.39/0.42 points absolute, respectively.