NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:6783
Title:Kernelized Bayesian Softmax for Text Generation

This work proposes an approach to accommodate multiple senses of words as different embeddings. Reviewers' positive assessment was influenced by the additional experiments and results provided in the authors' response, so authors are definitely expected to incorporate those (or results to the same effect) in the final version.