We sincerely thank all the reviewers for their insightful suggestions. We will add them back in the updated version, which will have 1 more page. Finally, we relax BERT and fine-tune the two models jointly. Results are shown in Table 1. As can be seen, this auxiliary training objective introduces a +0.8 F1 performance boost.

We sincerely thank all the reviewers for their insightful suggestions. We will add them back in the updated version, which will have 1 more page. Finally, we relax BERT and fine-tune the two models jointly. Results are shown in Table 1. As can be seen, this auxiliary training objective introduces a +0.8 F1 performance boost.

The consensus appears to be that this is a "well written" (R1, R2, R3, R4) paper that introduces a "simple yet effective module" (R1) to solve an "important problem" We kindly address the reviewers' questions below. Following our inquiry, the authors of IODINE updated their paper. The strength of our method rather lies in its simplicity, efficiency, and flexibility. Slot Attention achieves 69 .4 Results on MONet were not reported.