Text Embedding with Transformers

author: Jael Gu and David Wang

Desription

A REALM[1] text embedding operator implemented with pretrained models from Huggingface Transformers.

from towhee import ops

text_encoder = ops.text_embedding.realm('google/realm-cc-news-pretrained-encoder')
text_embedding = text_encoder("Hello, world.")

Factory Constructor

Create the operator via the following factory method

ops.text_embedding.realm(model_name)

Interface

A text embedding operator takes a sentence, paragraph, or document in string as an input and output an embedding vector in ndarray which captures the input's core semantic elements.

Parameters:

​ text: str

​ The text in string.

Returns: numpy.ndarray

​ The text embedding extracted by model.

Code Example

Use the pretrained model ('google/realm-cc-news-pretrained-encoder') to generate a text embedding for the sentence "Hello, world.".

Write the pipeline in simplified style:

import towhee.DataCollection as dc

dc.glob("Hello, world.")
  .text_embedding.realm('google/realm-cc-news-pretrained-encoder')
  .show()

Write a same pipeline with explicit inputs/outputs name specifications:

from towhee import DataCollection as dc

dc.glob['text']('Hello, world.')
  .text_embedding.realm['text', 'vec']('bert-base-cased')
  .select('vec')
  .show()

[1] https://arxiv.org/abs/2002.08909