No project description provided

Project description

Document Embeddings

Based on the results of: https://arxiv.org/abs/2304.14796

Implemented Methods

Average Pooling, with adjustable range for sentences used.
PERT weighted average pooling

Usage

Wrapper for Sentence-Embedding, which is used to provide embedding functionality

from sentence_transformers import SentenceTransformer

sentence_model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")

document_model = AverageDocumentEmbedding(sentence_model, language='german')


doc1 = "Arbitrary text"
doc2 = "..."

document_model.encode([doc1, doc2, ...])

Project details

Release history Release notifications | RSS feed

This version

0.0.1

Nov 7, 2023

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

document-embedding-0.0.1.tar.gz (3.9 kB view hashes)

Uploaded Nov 7, 2023 Source

Built Distribution

document_embedding-0.0.1-py3-none-any.whl (3.8 kB view hashes)

Uploaded Nov 7, 2023 Python 3

Hashes for document-embedding-0.0.1.tar.gz

Hashes for document-embedding-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`13da018fc42635ca56e72ed259ff729fcd20e46fb2016594ce56f8638e6453df`
MD5	`3d543a002099f61758d63312f7fe2532`
BLAKE2b-256	`fc1d10cdab5d52ae1c7bf234510ac8e5445234517b5359f7caaef32dcb38d692`

Hashes for document_embedding-0.0.1-py3-none-any.whl

Hashes for document_embedding-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`13f1e48734378f0d8b32cdbb8a5f659e40ae83aff3971d8dc33b9607bdaf4007`
MD5	`0d073d8af5402be81ef4e4be822c9361`
BLAKE2b-256	`172d737983a591c09999d27b2cd801eda15b786a3eef12afed8ba7119fc2871c`