实体命名识别(NER)如何入门?
分享一些NER的论文,从F1-Score、Wordunit、Word Emb、Charunit、Crf、Note、Efficiency、Gazetters和LM多个视角对比了14篇NER论文。14篇论文如下:
1、【LSTM-CRF (Lample et al., 2016)】 Bidirectional LSTM-CRF for Clinical Concept Extraction
2、【Ma and Hovy (2016)】 End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
3、【Transfer Learning Yang et al. (2017)】 Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
4、【NCRF++ (Yang and Zhang, 2018)】 NCRF++ An Open-source Neural Sequence Labeling Toolkit
5、【HSCRF (Ye and Ling, 2018)】 Hybrid semi-Markov CRF for Neural Sequence Labeling
6、【Chiu and Nichols (2016.6.19)】 Named Entity Recognition with Bidirectional LSTM-CNNs
7、【LM-LSTM-CRF (Liu et al., 2017)】Empower sequence labeling with task-aware neural language model
8、【Bi-LSTM-CRF + Lexical Features】Contextualized Word Representations from Distant Supervision with and for NER
9、【CRF + AutoEncoder (Wu et al., 2018)】Evaluating the Utility of Hand-crafted Features in Sequence Labelling
10、【TagLM】Semi-supervised sequence tagging with bidirectional language models
11、【BiLSTM -CRF+ ELMo】Deep contextualized word representations
12、【BERT Base (Devlin et al., 2018.10.11)】BERT Pre-training of Deep Bidirectional Transformers for Language Understanding
13、【CVT + Multi-Task】Semi-Supervised Sequence Modeling with Cross-View Training
14、【Flair embeddings (Akbik et al., 2018)】FLAIR An Easy-to-Use Framework for State-of-the-Art NLP