Declutr Base

🚀 DeCLUTR-base

DeCLUTR-base是一個用於句子相似度計算的模型，它基於深度對比學習，可作為通用句子編碼器，為文本提供高質量的向量表示。

🚀 快速開始

模型描述

“DeCLUTR-base” 模型來自我們的論文：DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations。

預期用途和侷限性

該模型旨在用作通用句子編碼器，類似於 Google的通用句子編碼器 或 Sentence Transformers。

如何使用

完整詳情請參閱 我們的倉庫。以下是簡單示例。

💻 使用示例

基礎用法

使用 SentenceTransformers

from scipy.spatial.distance import cosine
from sentence_transformers import SentenceTransformer

# 加載模型
model = SentenceTransformer("johngiorgi/declutr-base")

# 準備要嵌入的文本
texts = [
    "A smiling costumed woman is holding an umbrella.",
    "A happy woman in a fairy costume holds an umbrella.",
]

# 嵌入文本
embeddings = model.encode(texts)

# 通過餘弦距離計算語義相似度
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])

使用 🤗 Transformers

import torch
from scipy.spatial.distance import cosine
from transformers import AutoModel, AutoTokenizer

# 加載模型
tokenizer = AutoTokenizer.from_pretrained("johngiorgi/declutr-base")
model = AutoModel.from_pretrained("johngiorgi/declutr-base")

# 準備要嵌入的文本
text = [
    "A smiling costumed woman is holding an umbrella.",
    "A happy woman in a fairy costume holds an umbrella.",
]
inputs = tokenizer(text, padding=True, truncation=True, return_tensors="pt")

# 嵌入文本
with torch.no_grad():
    sequence_output = model(**inputs)[0]

# 對詞級嵌入進行平均池化以獲得句子級嵌入
embeddings = torch.sum(
    sequence_output * inputs["attention_mask"].unsqueeze(-1), dim=1
) / torch.clamp(torch.sum(inputs["attention_mask"], dim=1, keepdims=True), min=1e-9)

# 通過餘弦距離計算語義相似度
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])

BibTeX 引用和引用信息

@inproceedings{giorgi-etal-2021-declutr,
    title        = {{D}e{CLUTR}: Deep Contrastive Learning for Unsupervised Textual Representations},
    author       = {Giorgi, John  and Nitski, Osvald  and Wang, Bo  and Bader, Gary},
    year         = 2021,
    month        = aug,
    booktitle    = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
    publisher    = {Association for Computational Linguistics},
    address      = {Online},
    pages        = {879--895},
    doi          = {10.18653/v1/2021.acl-long.72},
    url          = {https://aclanthology.org/2021.acl-long.72}
}

📄 許可證

本項目採用 Apache 2.0 許可證。