End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF — mentioned by prions

Tue, 18 Dec 2018 19:08:11 GMT

I implemented a similar BiLSTM-CRF model at my current job. The architecture itself is really interesting, but runs into scaling issues. With LSTMs, you run into the constraint of having to wait on previous inputs and cache those results as well. Although TensorFlow now offers Cuda RNNS and fused kernels to speed up computation, I'd have thought for Amazon's scale, an attention/transformer based architcture would serve them better. I also notice a lot of dismissive comments about "black box models" or the simple solutions of just parsing out whitespace. My two cents: 1. Models with hand…

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

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF · HackerPapers discussions

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF — mentioned by prions