I am interested in comparing to your QuickThoughts method by evaluating it on the full SentEval benchmark. To do that I need to write something like the following:
def batcher(params, batch):
batch = [sent if sent != [] else ["."] for sent in batch]
embeddings = params.model.encode(batch)
embeddings = np.vstack(embeddings)
return embeddings
Is there a way for me to import your pre-trained model, and use it similar to the above code? E.g. is there a workflow for embedding lists of strings?
Hi,
I am interested in comparing to your QuickThoughts method by evaluating it on the full SentEval benchmark. To do that I need to write something like the following:
Is there a way for me to import your pre-trained model, and use it similar to the above code? E.g. is there a workflow for embedding lists of strings?