Search code examples
numpynlpconcatenationstanford-nlpword-embedding

How to concatenate Glove 100d embedding and 1d array which contains additional signal?

I new to NLP and trying out some text classification algorithms. I have 100d GloVe vector representing each entry as a list of embeddings. Also, I have NER feature of shape (2234,) which shows if there is named entity or not. Array with GloVe embeddings is of shape (2234, 100).

How to correctly concatenate these array so each row represents its word?

Sorry for not including reproducible example. Please, use variables of your choice to explain the concatenation procedure.

Using np.concatenate did not work as I have expected but i don't know how to deal with dimensionality of embeddings.

Solution

  • Just in case someone accidentally gets here. Use:

    my_arr.reshape(2234,1)

    Don't be me:)