Bidirectional LSTM-CRF Models for Sequence Tagging — mentioned by tensor

Fri, 04 May 2018 19:46:50 GMT

Can you provide articles comparing CRFs directly with LSTMs? Most articles on LSTMs don't actually compare against CRFs and an LSTM isn't a drop in replacement for a CRF. I haven't personally seen that neural networks have uniformly beaten CRFs on all tasks. E.g. [2] directly compares CRFs and an LSTM and the CRF achieves an F1 of 97.533 while the LSTM gets 97.848. In fact, because of the competitiveness of CRFs there are many works that combine them with neural networks (e.g. [2]) [1] https://arxiv.org/pdf/1606.03475.pdf [2] https://arxiv.org/abs/1508.01991

Paper and discussion history. A mention is not an endorsement.

Bidirectional LSTM-CRF Models for Sequence Tagging · HackerPapers discussions

Bidirectional LSTM-CRF Models for Sequence Tagging — mentioned by tensor