Reviews: Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks

Post-feedback update: Thank you for your update. Your additional results will strengthen this paper, and I still think it should be accepted. Specifically, it combines the basic overall framework for SPEN training using a reward signal introduced by [1] with the idea of adding in random search to find reward scoring violations, which has been used in the past by various papers (which are cited appropriately in this work). However, this exact combination is novel. Quality: The motivation behind using random search to augment the generation of labels to use for training the model is sound and verified empirically. Numerous appropriate baselines are included, ranging from beam search-type approaches to more directly comparable approaches such as [1], and the introduced approach outperforms all of them.