Olzhas Kabdolov


2018

pdf bib
Reproducing and Regularizing the SCRN Model
Olzhas Kabdolov | Zhenisbek Assylbekov | Rustem Takhanov
Proceedings of the 27th International Conference on Computational Linguistics

We reproduce the Structurally Constrained Recurrent Network (SCRN) model, and then regularize it using the existing widespread techniques, such as naive dropout, variational dropout, and weight tying. We show that when regularized and optimized appropriately the SCRN model can achieve performance comparable with the ubiquitous LSTM model in language modeling task on English data, while outperforming it on non-English data.