detext
detext copied to clipboard
linkedin
DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks
Has anyone tried getting clone of Github code and using it with TF 2.0? If yes, did it work? Which version of python version is compatible with it?
I am trying to run query autocomplete. Unable to run the line `args = DetextArg(ftr_ext="cnn", num_filters=50, num_units=64, emb_sim_func=["inner"], # cosine matching function ltr_loss_fn="softmax", # learning-to-rank loss optimizer="bert_adam", # same AdamWeightDecay...
Hi,I'm confused about how to generate the wide sparse features. Here is my understanding: combine the multi field categorical features together and form the multi hot sparse feature. then the...
Hello, I'm trying to use detext 3.0.0, so far it seems that I could train a model, however all examples under https://github.com/linkedin/detext/tree/master/user_guide/notebooks are still for TF1. Could you please add...
Hi, I am stuck at this point: No matching distribution found for tensorflow==1.14.0
As many companies are migrating to TF2.0.
Can you address a couple of instances of language in the project where the wording can be made more inclusive? (example: whiltelist -> allowlist). We are trying to make the...
# Description Added multi-label classification task to detext. Updated input label format to array (shape [num_classes], assuming one-hot array input), changed loss and activation functions, added precision/recall metrics. Passed unit...
