Bidirectional LSTM-CRF Models for Sequence Tagging

Abstract

we propose a variety of Long Short-Term Memory (LSTM) based models for sequence tagging.

LSTM networks

bidirectional LSTM (BI-LSTM) networks

LSTM with a Conditional Random Field (CRF) layer (LSTM-CRF)

bidirectional LSTM with a CRF layer (BI-LSTM-CRF).

The BI-LSTM-CRF model can produce state of the art (or close to) accuracy on POS, chunking and NER data sets.

6 Conclusion

Our model can produce state of the art (or close to) accuracy on POS, chunking and NER data sets.

Table 4 (accuracy), 6 (f1)

Figure 7（モデルの図）

conll2003使っている

Table 2