Bidirectional LSTM-CRF Model

A Bidirectional LSTM-CRF Model is a hybrid sequence learning model that combines a Bi-LSTM with a CRF model.

• Context:
  • It can be trained by a Bidirectional LSTM/CRF Training System (that implements a bidirectional LSTM/CRF training algorithm).
  • …
• Example(s)
  • a BiLSTM-CNN-CRF.
  • …
• Counter-Example(s):
  • BiLSTM-CNN,
  • BiLSTM-WSD,
  • SBU-LSTM.
• See: Bidirectional LSTM, CRF Training Task, Bidirectional RNN.

---

---

References

2017

• (Sterbak, 2017) ⇒ Tobias Sterbak (2017). Sequence Tagging With A LSTM-CRF: https://www.depends-on-the-definition.com/sequence-tagging-lstm-crf/
  • QUOTE: Now we use a hybrid approach combining a bidirectional LSTM model and a CRF model. The so called LSTM-CRF is a state-of-the-art approach to named entity recognition.

2015

• (Huang, Xu & Yu, 2015) ⇒ Zhiheng Huang, Wei Xu, Kai Yu (2015). "Bidirectional LSTM-CRF models for sequence tagging (PDF)". arXiv preprint arXiv:1508.01991.
  • QUOTE: Similar to a LSTM-CRF network, we combine a bidirectional LSTM network and a CRF network to form a BI-LSTM-CRF network (Fig. 7). In addition to the past input features and sentence level tag information used in a LSTM-CRF model, a BILSTM-CRF model can use the future input features. The extra features can boost tagging accuracy as we will show in experiments.
    

    Figure 7: A BI-LSTM-CRF model

---