Closed dkajtoch closed 4 years ago
Hi @dkajtoch thanks for the great question. The information is available in the caption of Figure 2b. We use "input embeddings" between the application word and context words, and a combination of input and output embeddings for the context words and materials. This pretty much translates to "which words that are similar to the application word is this material likely to be mentioned with". I hope this helps.
Closing this issue since the discussion seems to have been resolved, but please feel free to reopen if you want to continue.
I have a question about your research approach communicated in Nature. You use there phrases "target word" and "context word". Normally, in the skip-gram model embedding for the "target word" (input layer) is different that the embedding for the "context word" (output layer). In gensim if you use
model.wv.most_similar
you are effectively searching for similar words using embeddings from the input layer. You can also access "context word" embeddings viamodel.syn1neg
. Where you using both embeddings for analyzing e.g. relation between chemical compound and "thermoelectric"?