paraphrase-multilingual-miniLM-L12-v2-mnrl-beir

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the statictable-triplets-all dataset. It maps sentences & paragraphs to a 384-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/paraphrase-multilingual-MiniLM-L12-v2 <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • statictable-triplets-all

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

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("yahyaabd/paraphrase-multilingual-miniLM-L12-v2-mnrl-beir")
# Run inference
sentences = [
    'Bagaimana tren ekspor teh Indonesia ke berbagai negara tahun 2008?',
    'Ekspor Teh Menurut Negara Tujuan Utama, 2000-2015',
    'Luas Kawasan Hutan dan Kawasan Konservasi Perairan Indonesia Berdasarkan Surat Keputusan Menteri Lingkungan Hidup dan Kehutanan, 2017-2022',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Dataset: bps-statictable-ir
• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

statictable-triplets-all

• Dataset: statictable-triplets-all at 24979b4
• Size: 967,831 training samples
• Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
• Approximate statistics based on the first 1000 samples:

  	query	pos	neg
  type	string	string	string
  details	<ul><li>min: 5 tokens</li><li>mean: 18.53 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 25.42 tokens</li><li>max: 58 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 25.71 tokens</li><li>max: 58 tokens</li></ul>

• Samples:

  query	pos	neg
  <code>Data pendapatan per kapita, bedakan per golongan rumah tangga (ribu rupiah), 2008</code>	<code>Rata-rata Jumlah Pendapatan perkapita Menurut Golongan Rumah Tangga (ribu rupiah), 2000, 2005, 2008</code>	<code>Ringkasan Neraca Arus Dana, Triwulan II, 2007, (Miliar Rupiah)</code>
  <code>Berapa ribu ton impor Indonesia dari negara-negara utama tahun 2018?</code>	<code>Volume Impor Menurut Negara Asal Utama (Berat bersih:ribu ton), 2017-2023</code>	<code>Rata-Rata Pengeluaran Konsumsi per Kapita Menurut Golongan Rumah Tangga (ribu rupiah), 2000, 2005, dan 2008</code>
  <code>Kredit dari lembaga keuangan non-bank 2000-2016</code>	<code>Pemberian Kredit oleh Lembaga-Lembaga Keuangan Lainnya (miliar rupiah), 2000-2016</code>	<code>Angka Partisipasi Sekolah (APS) Penduduk Umur 7-18 Tahun Menurut Klasifikasi Desa, Jenis Kelamin, dan Kelompok Umur, 2009-2023</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

statictable-triplets-all

• Dataset: statictable-triplets-all at 24979b4
• Size: 967,831 evaluation samples
• Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
• Approximate statistics based on the first 1000 samples:

  	query	pos	neg
  type	string	string	string
  details	<ul><li>min: 5 tokens</li><li>mean: 18.75 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 25.35 tokens</li><li>max: 58 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 25.44 tokens</li><li>max: 58 tokens</li></ul>

• Samples:

  query	pos	neg
  <code>Bagaimana kebiasaan rumah tangga memisahkan sampah (mudah busuk vs tidak), per provinsi, 2021?</code>	<code>Persentase Rumah Tangga Menurut Provinsi dan Perlakuan Memilah Sampah Mudah Membusuk dan Tidak Mudah Membusuk, 2013-2014, 2021</code>	<code>Rata-Rata Upah/Gaji Bersih Sebulan (rupiah) Buruh/Karyawan/Pegawai menurut Provinsi dan Lapangan Pekerjaan Utama di 17 Sektor, 2023</code>
  <code>Bagaimana rincian pinjaman investasi (hanya Rupiah) dari bank umum ke berbagai sektor ekonomi pada tahun 2016?</code>	<code>Pinjaman Investasi Bank-Bank Umum dalam Rupiah Menurut Sektor Ekonomi (miliar rupiah), 2000 - 2016</code>	<code>Ringkasan Neraca Arus Dana, Triwulan IV, 2009, (Miliar Rupiah)</code>
  <code>Data rumah tangga per provinsi, adakah area serapan air? Ambil tahun 2013</code>	<code>Persentase Rumah Tangga Menurut Provinsi dan Keberadaan Area Resapan Air, 2013-2014</code>	<code>Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 (9 x 9)</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Logs

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.3.0
• Datasets: 3.4.1
• Tokenizers: 0.21.1

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",
}

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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->