Abstract
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 http://pytorch.org/, 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.- Anthology ID:
- P18-4013
- Volume:
- Proceedings of ACL 2018, System Demonstrations
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 74–79
- Language:
- URL:
- https://aclanthology.org/P18-4013
- DOI:
- 10.18653/v1/P18-4013
- Cite (ACL):
- Jie Yang and Yue Zhang. 2018. NCRF++: An Open-source Neural Sequence Labeling Toolkit. In Proceedings of ACL 2018, System Demonstrations, pages 74–79, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- NCRF++: An Open-source Neural Sequence Labeling Toolkit (Yang & Zhang, ACL 2018)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/P18-4013.pdf
- Code
- jiesutd/NCRFpp + additional community code
- Data
- CoNLL-2003, Penn Treebank