SentenceTransformer based on sentence-transformers/LaBSE

This is a sentence-transformers model finetuned from sentence-transformers/LaBSE on the Omartificial-Intelligence-Space/arabic-n_li-triplet dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/LaBSE
Maximum Sequence Length: 256 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- Omartificial-Intelligence-Space/arabic-n_li-triplet

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Omartificial-Intelligence-Space/Arabic-labse")
# Run inference
sentences = [
    'يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شابة.',
    'ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه',
    'الشاب نائم بينما الأم تقود ابنتها إلى الحديقة',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7269
spearman_cosine	0.7225
pearson_manhattan	0.7259
spearman_manhattan	0.721
pearson_euclidean	0.726
spearman_euclidean	0.7225
pearson_dot	0.7269
spearman_dot	0.7225
pearson_max	0.7269
spearman_max	0.7225

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7268
spearman_cosine	0.7224
pearson_manhattan	0.7241
spearman_manhattan	0.7195
pearson_euclidean	0.7248
spearman_euclidean	0.7213
pearson_dot	0.7253
spearman_dot	0.7205
pearson_max	0.7268
spearman_max	0.7224

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7283
spearman_cosine	0.7264
pearson_manhattan	0.7228
spearman_manhattan	0.7181
pearson_euclidean	0.7251
spearman_euclidean	0.7215
pearson_dot	0.7243
spearman_dot	0.7221
pearson_max	0.7283
spearman_max	0.7264

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7102
spearman_cosine	0.7104
pearson_manhattan	0.7135
spearman_manhattan	0.7089
pearson_euclidean	0.7172
spearman_euclidean	0.713
pearson_dot	0.6778
spearman_dot	0.6746
pearson_max	0.7172
spearman_max	0.713

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6931
spearman_cosine	0.6982
pearson_manhattan	0.6971
spearman_manhattan	0.6942
pearson_euclidean	0.7013
spearman_euclidean	0.6987
pearson_dot	0.6377
spearman_dot	0.6345
pearson_max	0.7013
spearman_max	0.6987

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8144
spearman_cosine	0.8205
pearson_manhattan	0.8203
spearman_manhattan	0.8204
pearson_euclidean	0.8202
spearman_euclidean	0.8205
pearson_dot	0.8144
spearman_dot	0.8205
pearson_max	0.8203
spearman_max	0.8205

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8143
spearman_cosine	0.8212
pearson_manhattan	0.8217
spearman_manhattan	0.8216
pearson_euclidean	0.8216
spearman_euclidean	0.8219
pearson_dot	0.8097
spearman_dot	0.8147
pearson_max	0.8217
spearman_max	0.8219

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8076
spearman_cosine	0.8159
pearson_manhattan	0.8209
spearman_manhattan	0.8197
pearson_euclidean	0.821
spearman_euclidean	0.8203
pearson_dot	0.7871
spearman_dot	0.7875
pearson_max	0.821
spearman_max	0.8203

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8024
spearman_cosine	0.8118
pearson_manhattan	0.8189
spearman_manhattan	0.8181
pearson_euclidean	0.8198
spearman_euclidean	0.8185
pearson_dot	0.7513
spearman_dot	0.7428
pearson_max	0.8198
spearman_max	0.8185

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7855
spearman_cosine	0.7949
pearson_manhattan	0.806
spearman_manhattan	0.8041
pearson_euclidean	0.8088
spearman_euclidean	0.806
pearson_dot	0.6778
spearman_dot	0.6616
pearson_max	0.8088
spearman_max	0.806

Training Details

Training Dataset

Omartificial-Intelligence-Space/arabic-n_li-triplet

Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
Size: 557,850 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 4 tokens mean: 9.99 tokens max: 51 tokens	min: 4 tokens mean: 12.44 tokens max: 49 tokens	min: 5 tokens mean: 13.82 tokens max: 49 tokens

Samples:

anchor	positive	negative
`شخص على حصان يقفز فوق طائرة معطلة`	`شخص في الهواء الطلق، على حصان.`	`شخص في مطعم، يطلب عجة.`
`أطفال يبتسمون و يلوحون للكاميرا`	`هناك أطفال حاضرون`	`الاطفال يتجهمون`
`صبي يقفز على لوح التزلج في منتصف الجسر الأحمر.`	`الفتى يقوم بخدعة التزلج`	`الصبي يتزلج على الرصيف`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

Omartificial-Intelligence-Space/arabic-n_li-triplet

Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
Size: 6,584 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 4 tokens mean: 19.71 tokens max: 100 tokens	min: 4 tokens mean: 9.37 tokens max: 38 tokens	min: 4 tokens mean: 10.49 tokens max: 34 tokens

Samples:

anchor	positive	negative
`امرأتان يتعانقان بينما يحملان حزمة`	`إمرأتان يحملان حزمة`	`الرجال يتشاجرون خارج مطعم`
`طفلين صغيرين يرتديان قميصاً أزرق، أحدهما يرتدي الرقم 9 والآخر يرتدي الرقم 2 يقفان على خطوات خشبية في الحمام ويغسلان أيديهما في المغسلة.`	`طفلين يرتديان قميصاً مرقماً يغسلون أيديهم`	`طفلين يرتديان سترة يذهبان إلى المدرسة`
`رجل يبيع الدونات لعميل خلال معرض عالمي أقيم في مدينة أنجليس`	`رجل يبيع الدونات لعميل`	`امرأة تشرب قهوتها في مقهى صغير`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 64
per_device_eval_batch_size: 64
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	sts-test-128_spearman_cosine	sts-test-256_spearman_cosine	sts-test-512_spearman_cosine	sts-test-64_spearman_cosine	sts-test-768_spearman_cosine
None	0	-	0.7104	0.7264	0.7224	0.6982	0.7225
0.0229	200	13.1738	-	-	-	-	-
0.0459	400	8.8127	-	-	-	-	-
0.0688	600	8.0984	-	-	-	-	-
0.0918	800	7.2984	-	-	-	-	-
0.1147	1000	7.5749	-	-	-	-	-
0.1377	1200	7.1292	-	-	-	-	-
0.1606	1400	6.6146	-	-	-	-	-
0.1835	1600	6.6523	-	-	-	-	-
0.2065	1800	6.1095	-	-	-	-	-
0.2294	2000	6.0841	-	-	-	-	-
0.2524	2200	6.3024	-	-	-	-	-
0.2753	2400	6.1941	-	-	-	-	-
0.2983	2600	6.1686	-	-	-	-	-
0.3212	2800	5.8317	-	-	-	-	-
0.3442	3000	6.0597	-	-	-	-	-
0.3671	3200	5.7832	-	-	-	-	-
0.3900	3400	5.7088	-	-	-	-	-
0.4130	3600	5.6988	-	-	-	-	-
0.4359	3800	5.5268	-	-	-	-	-
0.4589	4000	5.5543	-	-	-	-	-
0.4818	4200	5.3152	-	-	-	-	-
0.5048	4400	5.2894	-	-	-	-	-
0.5277	4600	5.1805	-	-	-	-	-
0.5506	4800	5.4559	-	-	-	-	-
0.5736	5000	5.3836	-	-	-	-	-
0.5965	5200	5.2626	-	-	-	-	-
0.6195	5400	5.2511	-	-	-	-	-
0.6424	5600	5.3308	-	-	-	-	-
0.6654	5800	5.2264	-	-	-	-	-
0.6883	6000	5.2881	-	-	-	-	-
0.7113	6200	5.1349	-	-	-	-	-
0.7342	6400	5.0872	-	-	-	-	-
0.7571	6600	4.5515	-	-	-	-	-
0.7801	6800	3.4312	-	-	-	-	-
0.8030	7000	3.1008	-	-	-	-	-
0.8260	7200	2.9582	-	-	-	-	-
0.8489	7400	2.8153	-	-	-	-	-
0.8719	7600	2.7214	-	-	-	-	-
0.8948	7800	2.5392	-	-	-	-	-
0.9177	8000	2.584	-	-	-	-	-
0.9407	8200	2.5384	-	-	-	-	-
0.9636	8400	2.4937	-	-	-	-	-
0.9866	8600	2.4155	-	-	-	-	-
1.0	8717	-	0.8118	0.8159	0.8212	0.7949	0.8205

Framework Versions

Python: 3.9.18
Sentence Transformers: 3.0.1
Transformers: 4.40.0
PyTorch: 2.2.2+cu121
Accelerate: 0.26.1
Datasets: 2.19.0
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Acknowledgments

The author would like to thank Prince Sultan University for their invaluable support in this project. Their contributions and resources have been instrumental in the development and fine-tuning of these models.

## Citation

If you use the Arabic Matryoshka Embeddings Model, please cite it as follows:

@misc{nacar2024enhancingsemanticsimilarityunderstanding,
      title={Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning}, 
      author={Omer Nacar and Anis Koubaa},
      year={2024},
      eprint={2407.21139},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.21139}, 
}