1 . For all authors a

Do the main claims made in the abstract and introduction accurately reflect the paper's If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Y es] Provided in the Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? Did you include the total amount of compute and the type of resources used (e.g., type If you are using existing assets (e.g., code, data, models) or curating/releasing new assets... (a) If your work uses existing assets, did you cite the creators? Did you include any new assets either in the supplemental material or as a URL? [Y es] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) Figure 2 shows an overview of our proposed approach. Any number of differentiable constraints can be incorporated. D.1 Semantic similarity models We explain the semantic similarity models we use in our experiments in more detail here: 15 Weights Fluency (%) Transfer (%) wsim (w.r .t. input) wsim (w.r .t. ref.) log p ( y | x) We use this model for adding constraints in style-transfer ( 3.1) and D.2 Models used in multi-attribute transfer We collect Y elp restaurant reviews using scripts provided by Lample et al.