pith. sign in

arxiv: 1609.09007 · v1 · pith:5IM7G3VCnew · submitted 2016-09-28 · 💻 cs.CL · cs.LG

Unsupervised Neural Hidden Markov Models

classification 💻 cs.CL cs.LG
keywords approachhiddenmarkovmodelmodelsunsupervisedadditionalcompetitive
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.