This repository contains code that implements a sequential neural conditional random field (CRF) in DyNet. It can be trained using DyNet's autobatching (on CPU or GPU) to perform sequence labeling tasks such as named-entity recognition (NER) or part-of-speech (POS) tagging, for which demo data is provided.
See https://pytorch.org/tutorials/beginner/nlp/advanced_tutorial.html for a walk-through in the PyTorch framework.