Using fastText Sentence Vector as an Input Feature

Question

I want to use the fastText Sentence Vector as an input Feature.

vector = model.get_sentence_vector('Original Sentence')

I am attempting to perform Binary Classification of sentences using MLPs and will train the algorithm using the fixed sized feature generated by the above code. Is this a plausible thing to do?

Jindřich · Accepted Answer · 2020-05-13 07:56:36Z

1

You can take the mean of the word embeddings, i.e., tokenize the sentence, look up embeddings for all words computing an average. In this way, you will get a NumPy array that you can use as an input to whatever classifier you want. Depending on the classification task, it might be useful to remove function words first.

Gensim has a richer Python API than FastText itself. If you just want to quickly train a classifier, the best option is using the command line interface of FastText.

answered May 13, 2020 at 7:56

Jindřich

11.3k2 gold badges31 silver badges54 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Jovi DSilva Over a year ago

But can I use get_sentence_vector? I believe this also returns an averaging of words in the sentence.

Jindřich Over a year ago

Yes, it does the average plus some additional tricks L2 norms.

Collectives™ on Stack Overflow

Using fastText Sentence Vector as an Input Feature

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related