This paper presents a novel approach to recurrent neural network (RNN) regularization. Differently from the widely adopted dropout method, which is applied to forward connections of feed-forward architectures or RNNs, we propose to drop neurons directly in recurrent connections in a way that does not cause loss of long-term memory. Our approach is as easy to implement and apply as the regular feed-forward dropout and we demonstrate its effectiveness for Long Short-Term Memory network, the most popular type of RNN cells. Our experiments on three NLP benchmarks show consistent improvements even when combined with conventional feed-forward dropout.
|Title of host publication||Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers|
|Number of pages||10|
|Publisher||Association for Computational Linguistics (ACL)|
|Publication status||Published - 12.2016|
|Event||26th International Conference on Computational Linguistics - Osaka, Japan|
Duration: 11.12.2016 → 16.12.2016
Conference number: 136517