Approach to Sentence similarity algorithm

Question

I want to implement a sentence similarity algorithm. Is it possible to implement it using sequence prediction algorithm? If it is possible what kind of approach should i go forward with or is there any other method which is more suitable for sentence similarity algorithm ,please share your views.

score 2 · Accepted Answer · edited May 23 '17 at 10:29

2

You could try to treat your sentences as separate documents and then use traditional approach for finding similarity between documents. It was answered here using sklearn: Similarity between two text documents If you want, you could try and implement the same code in tensorflow.

I also strongly recommend to read this answer, which covers more sophisticated approaches: https://stackoverflow.com/a/15173821/3633250

edited May 23 '17 at 10:29

Community

1
1

answered Nov 19 '16 at 16:25

Maksim Khaitovich

4,610
5
37
65

Thanks for the info Maxim .One more question though on the first link you have mentioned ,are the solutions mentioned similar to word2vec conversion and should I drop the idea of using sequence prediction . – Aniruddh Nov 22 '16 at 08:20
@Aniruddh sorry, I didn't follow your second question - in your original question there is nothing about sequence prediction. – Maksim Khaitovich Nov 22 '16 at 15:22

score 1 · Answer 2 · answered Nov 22 '16 at 12:37

1

You could consider using Doc2Vec. Each sentence (document) is mapped to an n-dimensional space. To find the most similar document,

model.most_similar(“documentID”)

Reference

answered Nov 22 '16 at 12:37

user799188

13,097
3
31
36

Approach to Sentence similarity algorithm

2 Answers2