MaartenGr
Running Keybert for a list of docs to extract arabic keywords
Hi I have a list of arabic text and I want to extract keywords of each list element, for this I'm following the documentation ,
So I started by initiating the keybert model with this model
from keybert import KeyBERT kw_model = KeyBERT(model="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
then to extract doc and word embedding I did this
doc_embeddings, word_embeddings = kw_model.extract_embeddings(doc, min_df=1, stop_words= stp.stopwords_list()) with stp.stopwords_list() is my custom stop words for arabic
But this last line throws an error:
ValueError: not enough values to unpack (expected 2, got 0)
edit: doc is a list of text , len of doc is 108789, each text is an article
I didn't understand why this error and how to figure it out.
Thank you
Could you share your full code and error messages? That makes it a bit easier to understand what is happening here. Also, which version of KeyBERT are you using? Make sure to format everything with code blocks.
