Bert-as-service: How to obtain the word embeddings

[lucyboll]

Thanks for this service, I can get the sentence embeddings. I want to know how can I get the context representations for every token in the sentence through the service. Thank you very much.

[hanxiao]

good point. in principle, there is nothing stops us from getting the word embedding. I also understand the importance of this feature as people may want to use this service in an ELMO-like fashion. It's just the API and interface might be changed a little bit when considering word embedding.

So point taken, I will consider it as a feature and implement it soon.

[hanxiao]

@lucyboll fyi, this is done in v1.1, please check out latest master and this thread for more details.

close #25