sebischair / Lbl2Vec

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

https://wwwmatthes.in.tum.de/pages/naimi84squl1/Lbl2Vec-An-Embedding-based-Approach-for-Unsupervised-Document-Retrieval-on-Predefined-Topics

sebischair/Lbl2Vec Issues

ValueError: cannot compute mean with no input
Updated 5 months ago6
multiclass multilabel classification
Updated 7 months ago
Is it possible to use 2 words as keywords
Updated a year ago
Lbl2TransformerVec - predict_model_docs() when clean_outliers=True creates Dimension out of range
Updated 2 years ago1
Lbl2TransformerVec(Lbl2Vec).predict_model_docs() stalls / lack of GPU utilization
Updated 2 years ago
Saved the trained model using pickle (and also using the lbl2vec save feature) and when I tried to load in a custom module, it gives the following error "No module named lbl2vec.sav"
Updated 2 years ago
Is paragraph classification possible?
Updated 2 years ago
Multilingual?
Closed 2 years ago1
ValueError: cannot compute similarity with no input
Closed 2 years ago3
Localization possible ?
Closed 3 years ago2
pip install doesnt work
Closed 3 years ago2