NCRF++: An Open-source Neural Sequence Labeling Toolkit

ACL 2018  ·  Jie Yang, Yue Zhang ·

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.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Named Entity Recognition (NER) CoNLL 2003 (English) NCRF++ F1 91.35 # 61
Chunking Penn Treebank NCRF++ F1 score 95.06 # 7
Part-Of-Speech Tagging Penn Treebank NCRF++ Accuracy 97.49 # 14