I (complete noob in machine learning and natural language processing) am using doc2vec approach (gensim python library) to find most similar document to a random string. Problem is that whenever I'd like to add a new document to trained model I need to retrain model from scratch.
Is there an approach that stands out in ability to add a new document/vocabulary to a trained model without the need to train from scratch or an approach that would train faster?
I'm overwhelmed by all the approaches to nlp and only started with what I found as the most popular (word2vec/doc2vec) and now I'm looking for direction where to study now. Thanks for any recommendations.