DeCLUTR-base

Model description

The "DeCLUTR-base" model from our paper: DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations.

Intended uses & limitations

The model is intended to be used as a universal sentence encoder, similar to Google's Universal Sentence Encoder or Sentence Transformers.

How to use

Please see our repo for full details. A simple example is shown below.

With SentenceTransformers

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

# Load the model
model = SentenceTransformer("johngiorgi/declutr-base")

# Prepare some text to embed
texts = [
    "A smiling costumed woman is holding an umbrella.",
    "A happy woman in a fairy costume holds an umbrella.",
]

# Embed the text
embeddings = model.encode(texts)

# Compute a semantic similarity via the cosine distance
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])

With 🤗 Transformers

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

# Load the model
tokenizer = AutoTokenizer.from_pretrained("johngiorgi/declutr-base")
model = AutoModel.from_pretrained("johngiorgi/declutr-base")

# Prepare some text to embed
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")

# Embed the text
with torch.no_grad():
    sequence_output = model(**inputs)[0]

# Mean pool the token-level embeddings to get sentence-level embeddings
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)

# Compute a semantic similarity via the cosine distance
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])

BibTeX entry and citation info

@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}
}