best approach to embed random length sequences of words as a fixed size vector without having a maximum length? [closed]

Question

Closed. This question needs to be more focused. It is not currently accepting answers.

---

Want to improve this question? Update the question so it focuses on one problem only by editing this post.

Closed 4 months ago.

Improve this question

I have a dataset of sentences in a non-English language like:

1. word1 word2 word3 word62

2. word5 word1 word2

and the length of each sentence is not fixed.

Now, I want to represent each sentence as a fixed sized vector and give it to my model and i want to keep as much information as possible in the embedding, and i don't want to have a maximum length for sentences because important information might happen in the end.

The only two approaches I can think of so far are:

1. Convert them to one hot vector and add them

2. Convert them to a word embedding and then add them

Is there any better way? What is the best approach to represent a variable length sentence without losing information from it (like having a maximum length for each sentence - I want all the words in the sentence to affect the embedding)?

Answer 1

May be Universal Sentence Encoder might work for you if it can encode words in language you want. https://tfhub.dev/google/universal-sentence-encoder/4