Prannoy Mittal
Reputation: 1575
Building Vector for a sentence in doc2vec from an untrained data set
I have a doc2vec model build from my data, now I have a new sentence in run time which does not belong to the trained data set.
How can I build or predict a vector for this sentence from my model?
How should I handle unknown words in this sentence?
Upvotes: 2
Views: 1676
Answers (1)
kampta
Reputation: 4898
Gensim (development version) seems to have a method to infer vectors of new sentences. Check out model.infer_vector(NewDocument) method in https://github.com/gojomo/gensim/blob/develop/gensim/models/doc2vec.py
Upvotes: 4
Related Questions
- doc2vec infer words from vectors
- Word2vec on documents each one containing one sentence
- How to use Gensim doc2vec with pre-trained word vectors?
- Doc2Vec Pre training and Inferring vectors
- Gensim's Doc2Vec - How to use pre-trained word2vec (word similarities)
- How to use pretrained word2vec vectors in doc2vec model?
- Gensim Doc2Vec - Pass corpus sentences to Doc2Vec function
- doc2vec - Input Format for doc2vec training and infer_vector() in python
- Using gensim's Doc2Vec to produce sentence vectors
- Combining Doc2Vec sentences into paragraph vectors