Unsupervised Neural Hidden Markov Models
2016-09-28WS 2016Code Available0· sign in to hype
Ke Tran, Yonatan Bisk, Ashish Vaswani, Daniel Marcu, Kevin Knight
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ketranm/neuralHMMOfficialIn papertorch★ 0
- github.com/WinnieHAN/dnhmmtorch★ 0
Abstract
In this work, we present the first results for neuralizing an Unsupervised Hidden Markov Model. We evaluate our approach on tag in- duction. Our approach outperforms existing generative models and is competitive with the state-of-the-art though with a simpler model easily extended to include additional context.