jingyeom's picture
Update README.md
4c7891c verified
metadata
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity
  - mteb
model-index:
  - name: korean_embedding_model
    results:
      - task:
          type: STS
        dataset:
          type: mteb/biosses-sts
          name: MTEB BIOSSES
          config: default
          split: test
          revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
        metrics:
          - type: cos_sim_pearson
            value: 62.462024005162874
          - type: cos_sim_spearman
            value: 59.04592371468026
          - type: euclidean_pearson
            value: 60.118409297960774
          - type: euclidean_spearman
            value: 59.04592371468026
          - type: manhattan_pearson
            value: 59.6758261833799
          - type: manhattan_spearman
            value: 59.10255151100711
      - task:
          type: STS
        dataset:
          type: mteb/sickr-sts
          name: MTEB SICK-R
          config: default
          split: test
          revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
        metrics:
          - type: cos_sim_pearson
            value: 69.54306440280438
          - type: cos_sim_spearman
            value: 62.859142390813574
          - type: euclidean_pearson
            value: 65.6949193466544
          - type: euclidean_spearman
            value: 62.859152754778854
          - type: manhattan_pearson
            value: 65.65986839533139
          - type: manhattan_spearman
            value: 62.82868162534342
      - task:
          type: STS
        dataset:
          type: mteb/sts12-sts
          name: MTEB STS12
          config: default
          split: test
          revision: a0d554a64d88156834ff5ae9920b964011b16384
        metrics:
          - type: cos_sim_pearson
            value: 66.06384755873458
          - type: cos_sim_spearman
            value: 62.589736136651894
          - type: euclidean_pearson
            value: 62.78577890775041
          - type: euclidean_spearman
            value: 62.588858379781634
          - type: manhattan_pearson
            value: 62.827478623777985
          - type: manhattan_spearman
            value: 62.617997229102706
      - task:
          type: STS
        dataset:
          type: mteb/sts13-sts
          name: MTEB STS13
          config: default
          split: test
          revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
        metrics:
          - type: cos_sim_pearson
            value: 71.86398880834443
          - type: cos_sim_spearman
            value: 72.1348002553312
          - type: euclidean_pearson
            value: 71.6796109730168
          - type: euclidean_spearman
            value: 72.1349022685911
          - type: manhattan_pearson
            value: 71.66477952415218
          - type: manhattan_spearman
            value: 72.09093373400123
      - task:
          type: STS
        dataset:
          type: mteb/sts14-sts
          name: MTEB STS14
          config: default
          split: test
          revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
        metrics:
          - type: cos_sim_pearson
            value: 70.22680219584427
          - type: cos_sim_spearman
            value: 67.0818395499375
          - type: euclidean_pearson
            value: 68.24498247750782
          - type: euclidean_spearman
            value: 67.0818306104199
          - type: manhattan_pearson
            value: 68.23186143435814
          - type: manhattan_spearman
            value: 67.06973319437314
      - task:
          type: STS
        dataset:
          type: mteb/sts15-sts
          name: MTEB STS15
          config: default
          split: test
          revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
        metrics:
          - type: cos_sim_pearson
            value: 75.54853695205654
          - type: cos_sim_spearman
            value: 75.93775396598934
          - type: euclidean_pearson
            value: 75.10618334577337
          - type: euclidean_spearman
            value: 75.93775372510834
          - type: manhattan_pearson
            value: 75.123200749426
          - type: manhattan_spearman
            value: 75.95755907955946
      - task:
          type: STS
        dataset:
          type: mteb/sts16-sts
          name: MTEB STS16
          config: default
          split: test
          revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
        metrics:
          - type: cos_sim_pearson
            value: 70.22928051288379
          - type: cos_sim_spearman
            value: 70.13385961598065
          - type: euclidean_pearson
            value: 69.66948135244029
          - type: euclidean_spearman
            value: 70.13385923761084
          - type: manhattan_pearson
            value: 69.66975130970742
          - type: manhattan_spearman
            value: 70.16415157887303
      - task:
          type: STS
        dataset:
          type: mteb/sts17-crosslingual-sts
          name: MTEB STS17 (en-en)
          config: en-en
          split: test
          revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
        metrics:
          - type: cos_sim_pearson
            value: 77.12344529924287
          - type: cos_sim_spearman
            value: 77.13355009366349
          - type: euclidean_pearson
            value: 77.73092283054677
          - type: euclidean_spearman
            value: 77.13355009366349
          - type: manhattan_pearson
            value: 77.59037018668798
          - type: manhattan_spearman
            value: 77.00181739561044
      - task:
          type: STS
        dataset:
          type: mteb/sts22-crosslingual-sts
          name: MTEB STS22 (en)
          config: en
          split: test
          revision: eea2b4fe26a775864c896887d910b76a8098ad3f
        metrics:
          - type: cos_sim_pearson
            value: 60.402875441797896
          - type: cos_sim_spearman
            value: 62.21971197434699
          - type: euclidean_pearson
            value: 63.08540172189354
          - type: euclidean_spearman
            value: 62.21971197434699
          - type: manhattan_pearson
            value: 62.971870200624714
          - type: manhattan_spearman
            value: 62.17079870601948
      - task:
          type: STS
        dataset:
          type: mteb/stsbenchmark-sts
          name: MTEB STSBenchmark
          config: default
          split: test
          revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
        metrics:
          - type: cos_sim_pearson
            value: 69.14110875934769
          - type: cos_sim_spearman
            value: 67.83869999603111
          - type: euclidean_pearson
            value: 68.32930987602938
          - type: euclidean_spearman
            value: 67.8387112205369
          - type: manhattan_pearson
            value: 68.385068161592
          - type: manhattan_spearman
            value: 67.86635507968924
      - task:
          type: Summarization
        dataset:
          type: mteb/summeval
          name: MTEB SummEval
          config: default
          split: test
          revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
        metrics:
          - type: cos_sim_pearson
            value: 29.185534982566132
          - type: cos_sim_spearman
            value: 28.71714958933386
          - type: dot_pearson
            value: 29.185527195235316
          - type: dot_spearman
            value: 28.71714958933386

{MODEL_NAME}

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.

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('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

Evaluation Results

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

Full Model Architecture

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

Citing & Authors