LiyuanLucasLiu/LM-LSTM-CRF

This project provides high-performance character-aware sequence labeling tools, including Training, Evaluation and Prediction. Details about LM-LSTM-CRF can be accessed here, and the implementation is based on the PyTorch library. Our model achieves F1 score of 91.71 /-0.10 on the CoNLL 2003 NER dataset, without using any additional corpus or resource. The documents would be available here. As visualized above, we use conditional random field (CRF) to capture label dependencies, and adopt a hierarchical LSTM to leverage both char-level and word-level inputs.