Edit model card

German_Semantic_STS_V2

Note: Check out my new, updated models: German_Semantic_V3 and V3b!

This model creates german embeddings for semantic use cases.

This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Special thanks to deepset for providing the model gBERT-large and also to Philip May for the Translation of the dataset and chats about the topic.

Model score after fine-tuning scores best, compared to these models:

Model Name Spearman
xlm-r-distilroberta-base-paraphrase-v1 0.8079
xlm-r-100langs-bert-base-nli-stsb-mean-tokens 0.7877
xlm-r-bert-base-nli-stsb-mean-tokens 0.7877
roberta-large-nli-stsb-mean-tokens 0.6371
T-Systems-onsite/
german-roberta-sentence-transformer-v2
0.8529
paraphrase-multilingual-mpnet-base-v2 0.8355
T-Systems-onsite/
cross-en-de-roberta-sentence-transformer
0.8550
aari1995/German_Semantic_STS_V2 0.8626

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('aari1995/German_Semantic_STS_V2')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('aari1995/German_Semantic_STS_V2')
model = AutoModel.from_pretrained('aari1995/German_Semantic_STS_V2')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 1438 with parameters:

{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss with parameters:

{'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}

Parameters of the fit()-Method:

{
    "epochs": 4,
    "evaluation_steps": 500,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 5e-06
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 576,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

The base model is trained by deepset. The dataset was published / translated by Philip May. The model was fine-tuned by Aaron Chibb.

Downloads last month
24,808
Safetensors
Model size
336M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train aari1995/German_Semantic_STS_V2

Spaces using aari1995/German_Semantic_STS_V2 4

Collection including aari1995/German_Semantic_STS_V2

Evaluation results