Open
Description
Background and Feature Description
The universal-sentence-encoder model can generate text embeddings, and it depends on TensorFlow Text. Is TensorFlow Text supported?
https://tfhub.dev/google/universal-sentence-encoder-multilingual-large/3
API Definition and Usage
import tensorflow_hub as hub
import numpy as np
import tensorflow_text
# Some texts of different lengths.
english_sentences = ["dog", "Puppies are nice.", "I enjoy taking long walks along the beach with my dog."]
italian_sentences = ["cane", "I cuccioli sono carini.", "Mi piace fare lunghe passeggiate lungo la spiaggia con il mio cane."]
japanese_sentences = ["犬", "子犬はいいです", "私は犬と一緒にビーチを散歩するのが好きです"]
chinese_sentences = ["狗"，"小狗很好，我喜欢和我的狗一起沿着海滩散步"]
embed = hub.load("https://tfhub.dev/google/universal-sentence-encoder-multilingual-large/3")
# Compute embeddings.
en_result = embed(english_sentences)
it_result = embed(italian_sentences)
ja_result = embed(japanese_sentences)
# Compute similarity matrix. Higher score indicates greater similarity.
similarity_matrix_it = np.inner(en_result, it_result)
similarity_matrix_ja = np.inner(en_result, ja_result)Alternatives
No response
Risks
No response