Just get embedding for context and target word

[drussellmrichie]

Hi, I'm sorry if this is obvious, but how would I just get the embeddings for a context and for a potential target word?

For example, suppose my context is ['river', 'bank'] and my target is ['water']. How would I get vectors for each.....?

[orenmel]

See how target_v and context_v are obtained in explore_context2vec.py. Please note that in context2vec, the context representation is an ordered sequence of words with a specific 'missing' target word position specified, so just ['river', 'bank'] is not a valid context.

[drussellmrichie]

Thanks for the response. I'll take a look at that.

As for your point about how context representations are constructed, is there some reason I can't just represent my context as something like 'river bank []' as if it were a complete sentence?

[orenmel]

context2vec will interpret the input 'river bank []' as the context of a last word in a sentence that starts with 'river bank'. Please read the paper for a detailed explanation. If you don't care about specific position-within-sequence context representation then you might want to use a different model.