Skip to content

justanotherminh/Deep-maximum-entropy-Markov-model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Deep maximum entropy Markov model

A PyTorch implementation of the DMEMM model for NER tagging, with inference using the Viterbi algorithm

A Maximum entropy Markov model (MEMM) conditions the probability of a tag on the previous tag and the current input. A DMEMM uses a neural network to approximate this probability distribution. The input can be raw word vectors or contextualized vectors produced by a BiLSTM.

About

A PyTorch implementation of the DMEMM model for NER tagging

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages