NCRF++: An Open-source Neural Sequence Labeling Toolkit
Singapore University of Technology and Design
arXiv:1806.05626 [cs.CL], (14 Jun 2018)
@article{yang2018ncrf,
title={NCRF++: An Open-source Neural Sequence Labeling Toolkit},
author={Yang, Jie and Zhang, Yue},
year={2018},
month={jun},
archivePrefix={"arXiv"},
primaryClass={cs.CL}
}
This paper describes NCRF++, a toolkit for neural sequence labeling. NCRF++ is designed for quick implementation of different neural sequence labeling models with a CRF inference layer. It provides users with an inference for building the custom model structure through configuration file with flexible neural feature design and utilization. Built on PyTorch, the core operations are calculated in batch, making the toolkit efficient with the acceleration of GPU. It also includes the implementations of most state-of-the-art neural sequence labeling models such as LSTM-CRF, facilitating reproducing and refinement on those methods.
June 17, 2018 by hgpu
