longformer/README.md

Text Embedding with dpr

author: Kyle He

Desription

This operator uses Longformer to convert long text to embeddings.

The Longformer model was presented in Longformer: The Long-Document Transformer by Iz Beltagy, Matthew E. Peters, Arman Cohan[1].

Longformer models were proposed in “[Longformer: The Long-Document Transformer][2].

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism that scales linearly with sequence length, making it easy to process documents of thousands of tokens or longer[2].

Reference

[1].https://huggingface.co/docs/transformers/v4.16.2/en/model_doc/longformer#transformers.LongformerConfig

[2].https://arxiv.org/pdf/2004.05150.pdf

Code Example

Use the pretrained model "facebook/dpr-ctx_encoder-single-nq-base" to generate a text embedding for the sentence "Hello, world.".

Write the pipeline:

from towhee import dc


dc.stream(["Hello, world."])
  .text_embedding.longformer("allenai/longformer-base-4096")
  .show()

Factory Constructor

Create the operator via the following factory method

text_embedding.dpr(model_name="allenai/longformer-base-4096")

Parameters:

​ model_name: str

​ The model name in string. The default value is "allenai/longformer-base-4096". You can get the list of supported model names by calling get_model_list from longformer.py.

Interface

The operator takes a text in string as input. It loads tokenizer and pre-trained model using model name. and then return text embedding in ndarray.

Parameters:

​ text: str

​ The text in string.

Returns:

​ numpy.ndarray

​ The text embedding extracted by model.