ML Research Wiki / Benchmarks / Chunking / Penn Treebank

Penn Treebank

Chunking Benchmark

Performance Over Time

📊 Showing 5 results | 📏 Metric: F1 score

Top Performing Models

Rank Model Paper F1 score Date Code
1 ACE Automated Concatenation of Embeddings for Structured Prediction 97.30 2020-10-10 📦 Alibaba-NLP/ACE 📦 zhaoyuesun/phee
2 JMT A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks 95.77 2016-11-05 📦 rubythonode/joint-many-task-model 📦 hassyGo/charNgram2vec
3 IntNet + BiLSTM-CRF Learning Better Internal Structure of Words for Sequence Labeling 95.29 2018-10-29 -
4 NCRF++ NCRF++: An Open-source Neural Sequence Labeling Toolkit 95.06 2018-06-14 📦 jiesutd/PyTorchSeqLabel 📦 jiesutd/NCRFpp 📦 jiesutd/Text-Attention-Heatmap-Visualization
5 BI-LSTM-CRF (Senna) (ours) Bidirectional LSTM-CRF Models for Sequence Tagging 94.46 2015-08-09 📦 determined22/zh-ner-tf 📦 guillaumegenthial/tf_ner 📦 baiyang2464/chatbot-base-on-Knowledge-Graph

All Papers (5)