0
$\begingroup$

I'm a beginner in NLP and deep learning fields, and have stacked with the phase how research and list up available and substitutional encoders and decoders.

For example, I read a thesis that Bidirectional LSTM and CRF were selected for named-entity recognition, like below.

Named entity recognition with bidirectional lstm+CRF (with tensorflow code) - NER

However, if my dataset and these encoders and decoders didn't show high performance, I need to try other encoders and decoders.

My question is:

When you have the specific NLP task, like NER, and dataset to train, how do you research applicable encoders and decoders?

$\endgroup$

1 Answer 1

0
$\begingroup$

I guess there is no universal solution for that. But I can explain my roadmap as NLP scientist. Firstly, I try to find the most common dataset for my task (NER in your case). Then, I search for the leaderboard which shows the best papers/models for that dataset. Finally, I try to figure out which makes their models best in the leaderboard. For example, here is the text summarization leaderboard: http://nlpprogress.com/english/summarization.html

I hope it is helpful for you.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.