Abstract
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 feedforward 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 the most effective modern recurrent network – Long Short-Term Memory network. Our experiments on three NLP benchmarks show consistent improvements even when combined with conventional feed-forward dropout.- Anthology ID:
- C16-1165
- Volume:
- Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Venue:
- COLING
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 1757–1766
- Language:
- URL:
- https://aclanthology.org/C16-1165
- DOI:
- Cite (ACL):
- Stanislau Semeniuta, Aliaksei Severyn, and Erhardt Barth. 2016. Recurrent Dropout without Memory Loss. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1757–1766, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Recurrent Dropout without Memory Loss (Semeniuta et al., COLING 2016)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/C16-1165.pdf
- Code
- stas-semeniuta/drop-rnn + additional community code