metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1658
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-l
widget:
  - source_sentence: >-
      How are representatives of Member States designated in relation to their
      contact responsibilities towards the Board and stakeholders?
    sentences:
      - >-
        4.

        Member States shall ensure that their representatives on the Board:

        (a) have the relevant competences and powers in their Member State so as
        to contribute actively to the achievement of the 

        Board’s tasks referred to in Article 66;

        (b) are designated as a single contact point vis-à-vis the Board and,
        where appropriate, taking into account Member States’ 

        needs, as a single contact point for stakeholders;

        OJ L, 12.7.2024

        EN

        ELI: http://data.europa.eu/eli/reg/2024/1689/oj

        95/144
      - >-
        43/144

        (54)

        Directive (EU) 2019/1937 of the European Parliament and of the Council
        of 23 October 2019 on the protection of persons who 

        report breaches of Union law (OJ L 305, 26.11.2019, p. 17).

        (55)

        OJ L 123, 12.5.2016, p. 1.

        (56)

        Regulation (EU) No 182/2011 of the European Parliament and of the
        Council of 16 February 2011 laying down the rules and 

        general principles concerning mechanisms for control by Member States of
        the Commission’s exercise of implementing powers (OJ 

        L 55, 28.2.2011, p. 13).
      - >-
        Article 65

        Establishment and structure of the European Artificial Intelligence
        Board

        1.

        A European Artificial Intelligence Board (the ‘Board’) is hereby
        established.

        2.

        The Board shall be composed of one representative per Member State. The
        European Data Protection Supervisor shall 

        participate as observer. The AI Office shall also attend the Board’s
        meetings, without taking part in the votes. Other national 

        and Union authorities, bodies or experts may be invited to the meetings
        by the Board on a case by case basis, where the 

        issues discussed are of relevance for them.

        3.

        Each representative shall be designated by their Member State for a
        period of three years, renewable once.

        4.
  - source_sentence: What criteria should be used to define an 'AI system' in this Regulation?
    sentences:
      - >-
        12.

        Notified bodies shall participate in coordination activities as referred
        to in Article 38. They shall also take part 

        directly, or be represented in, European standardisation organisations,
        or ensure that they are aware and up to date in 

        respect of relevant standards.

        Article 32

        Presumption of conformity with requirements relating to notified bodies

        Where a conformity assessment body demonstrates its conformity with the
        criteria laid down in the relevant harmonised 

        standards or parts thereof, the references of which have been published
        in the Official Journal of the European Union, it shall 

        be presumed to comply with the requirements set out in Article 31 in so
        far as the applicable harmonised standards cover 

        those requirements.

        EN
      - >-
        1.

        Providers of high-risk AI systems shall, upon a reasoned request by a
        competent authority, provide that authority all 

        the information and documentation necessary to demonstrate the
        conformity of the high-risk AI system with the 

        requirements set out in Section 2, in a language which can be easily
        understood by the authority in one of the official 

        languages of the institutions of the Union as indicated by the Member
        State concerned.

        2.

        Upon a reasoned request by a competent authority, providers shall also
        give the requesting competent authority, as 

        applicable, access to the automatically generated logs of the high-risk
        AI system referred to in Article 12(1), to the extent 

        such logs are under their control.

        3.
      - >-
        (12)

        The notion of ‘AI system’ in this Regulation should be clearly defined
        and should be closely aligned with the work of 

        international organisations working on AI to ensure legal certainty,
        facilitate international convergence and wide 

        acceptance, while providing the flexibility to accommodate the rapid
        technological developments in this field. 

        Moreover, the definition should be based on key characteristics of AI
        systems that distinguish it from simpler 

        traditional software systems or programming approaches and should not
        cover systems that are based on the rules 

        defined solely by natural persons to automatically execute operations. A
        key characteristic of AI systems is their
  - source_sentence: >-
      What conditions must be met for the use of a 'real-time' remote biometric
      identification system in publicly accessible spaces?
    sentences:
      - >-
        the relevant law enforcement authority has completed a fundamental
        rights impact assessment and, unless provided 

        otherwise in this Regulation, has registered the system in the database
        as set out in this Regulation. The reference 

        database of persons should be appropriate for each use case in each of
        the situations mentioned above.

        (35)

        Each use of a ‘real-time’ remote biometric identification system in
        publicly accessible spaces for the purpose of law 

        enforcement should be subject to an express and specific authorisation
        by a judicial authority or by an independent 

        administrative authority of a Member State whose decision is binding.
        Such authorisation should, in principle, be
      - >-
        (i)

        contribute to effective cooperation with the competent authorities of
        third countries and with international 

        organisations;

        (j)

        assist national competent authorities and the Commission in developing
        the organisational and technical expertise 

        required for the implementation of this Regulation, including by
        contributing to the assessment of training needs for 

        staff of Member States involved in implementing this Regulation;

        (k) assist the AI Office in supporting national competent authorities in
        the establishment and development of AI 

        regulatory sandboxes, and facilitate cooperation and information-sharing
        among AI regulatory sandboxes;

        (l)

        contribute to, and provide relevant advice on, the development of
        guidance documents;
      - >-
        referred to in Article 35 of Regulation (EU) 2016/679 and in Article 39
        of Regulation (EU) 2018/1725, may arise 

        during the sandbox experimentation, as well as response mechanisms to
        promptly mitigate those risks and, where 

        necessary, stop the processing;

        (d) any personal data to be processed in the context of the sandbox are
        in a functionally separate, isolated and protected 

        data processing environment under the control of the prospective
        provider and only authorised persons have access to 

        those data;

        (e) providers can further share the originally collected data only in
        accordance with Union data protection law; any 

        personal data created in the sandbox cannot be shared outside the
        sandbox;
  - source_sentence: >-
      What responsibilities does the AI Office have in monitoring
      general-purpose AI models according to the Regulation?
    sentences:
      - |-
        of the tasks of the scientific panel under Article 68(2).
        OJ L, 12.7.2024
        EN
        ELI: http://data.europa.eu/eli/reg/2024/1689/oj
        111/144
      - >-
        Commission. The AI Office should be able to carry out all necessary
        actions to monitor the effective implementation 

        of this Regulation as regards general-purpose AI models. It should be
        able to investigate possible infringements of 

        the rules on providers of general-purpose AI models both on its own
        initiative, following the results of its 

        monitoring activities, or upon request from market surveillance
        authorities in line with the conditions set out in this 

        Regulation. To support effective monitoring of the AI Office, it should
        provide for the possibility that downstream 

        providers lodge complaints about possible infringements of the rules on
        providers of general-purpose AI models and 

        systems.

        (163)
      - >-
        representative and importers accordingly.

        2.

        Where the high-risk AI system presents a risk within the meaning of
        Article 79(1) and the provider becomes aware of 

        that risk, it shall immediately investigate the causes, in collaboration
        with the reporting deployer, where applicable, and 

        inform the market surveillance authorities competent for the high-risk
        AI system concerned and, where applicable, the 

        notified body that issued a certificate for that high-risk AI system in
        accordance with Article 44, in particular, of the nature 

        of the non-compliance and of any relevant corrective action taken.

        Article 21

        Cooperation with competent authorities

        1.
  - source_sentence: >-
      What is the role of the Commission in assessing a harmonised standard
      proposed by a European standardisation organisation?
    sentences:
      - >-
        biometric identification systems in publicly accessible spaces for
        purposes other than law enforcement, including by 

        competent authorities, should not be covered by the specific framework
        regarding such use for the purpose of law 

        enforcement set by this Regulation. Such use for purposes other than law
        enforcement should therefore not be 

        subject to the requirement of an authorisation under this Regulation and
        the applicable detailed rules of national law 

        that may give effect to that authorisation.

        (39)

        Any processing of biometric data and other personal data involved in the
        use of AI systems for biometric 

        identification, other than in connection to the use of real-time remote
        biometric identification systems in publicly
      - >-
        Member States relating to the making available on the market of
        measuring instruments (OJ L 96, 29.3.2014, p. 149).
      - >-
        to in paragraph 1, or parts of those specifications, shall be presumed
        to be in conformity with the requirements set out in 

        Section 2 of this Chapter or, as applicable, to comply with the
        obligations referred to in Sections 2 and 3 of Chapter V, to 

        the extent those common specifications cover those requirements or those
        obligations.

        4.

        Where a harmonised standard is adopted by a European standardisation
        organisation and proposed to the 

        Commission for the publication of its reference in the Official Journal
        of the European Union, the Commission shall assess the 

        harmonised standard in accordance with Regulation (EU) No 1025/2012.
        When reference to a harmonised standard is
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.81
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.93
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.95
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.81
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30999999999999994
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18999999999999997
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09999999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.81
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.93
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.95
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9068999830894289
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8770119047619047
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8770119047619047
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-l

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-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: Snowflake/snowflake-arctic-embed-l
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): 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("KatGaw/eu-legal-ft-2")
# Run inference
sentences = [
    'What is the role of the Commission in assessing a harmonised standard proposed by a European standardisation organisation?',
    'to in paragraph 1, or parts of those specifications, shall be presumed to be in conformity with the requirements set out in \nSection 2 of this Chapter or, as applicable, to comply with the obligations referred to in Sections 2 and 3 of Chapter V, to \nthe extent those common specifications cover those requirements or those obligations.\n4.\nWhere a harmonised standard is adopted by a European standardisation organisation and proposed to the \nCommission for the publication of its reference in the Official Journal of the European Union, the Commission shall assess the \nharmonised standard in accordance with Regulation (EU) No 1025/2012. When reference to a harmonised standard is',
    'Member States relating to the making available on the market of measuring instruments (OJ L 96, 29.3.2014, p. 149).',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.81
cosine_accuracy@3	0.93
cosine_accuracy@5	0.95
cosine_accuracy@10	1.0
cosine_precision@1	0.81
cosine_precision@3	0.31
cosine_precision@5	0.19
cosine_precision@10	0.1
cosine_recall@1	0.81
cosine_recall@3	0.93
cosine_recall@5	0.95
cosine_recall@10	1.0
cosine_ndcg@10	0.9069
cosine_mrr@10	0.877
cosine_map@100	0.877

Training Details

Training Dataset

Unnamed Dataset

Size: 1,658 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 2 tokens
mean: 21.21 tokens
max: 44 tokens

min: 5 tokens
mean: 126.72 tokens
max: 217 tokens

	sentence_0	sentence_1
type	string	string
details	min: 2 tokens mean: 21.21 tokens max: 44 tokens	min: 5 tokens mean: 126.72 tokens max: 217 tokens

Samples:

sentence_0	sentence_1
`What documentation must the provider prepare according to Article 11 and Annex IV?`	`(b) the provider has drawn up the technical documentation in accordance with Article 11 and Annex IV; (c) the system bears the required CE marking and is accompanied by the EU declaration of conformity referred to in Article 47 and instructions for use; (d) the provider has appointed an authorised representative in accordance with Article 22(1). OJ L, 12.7.2024 EN ELI: http://data.europa.eu/eli/reg/2024/1689/oj 65/144`
`What must accompany the system alongside the CE marking as per the context provided?`	`(b) the provider has drawn up the technical documentation in accordance with Article 11 and Annex IV; (c) the system bears the required CE marking and is accompanied by the EU declaration of conformity referred to in Article 47 and instructions for use; (d) the provider has appointed an authorised representative in accordance with Article 22(1). OJ L, 12.7.2024 EN ELI: http://data.europa.eu/eli/reg/2024/1689/oj 65/144`
`What actions will the Commission take if there are doubts about a notified body's competence?`	1. The Commission shall, where necessary, investigate all cases where there are reasons to doubt the competence of a notified body or the continued fulfilment by a notified body of the requirements laid down in Article 31 and of its applicable responsibilities. 2. The notifying authority shall provide the Commission, on request, with all relevant information relating to the notification or the maintenance of the competence of the notified body concerned. 3. The Commission shall ensure that all sensitive information obtained in the course of its investigations pursuant to this Article is treated confidentially in accordance with Article 78. 4.

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

eval_strategy: steps
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
num_train_epochs: 30
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_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
num_train_epochs: 30
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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
restore_callback_states_from_checkpoint: 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: False
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, 'non_blocking': False, '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: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss	cosine_ndcg@10
0.3012	50	-	0.8523
0.6024	100	-	0.8744
0.9036	150	-	0.8993
1.0	166	-	0.9049
1.2048	200	-	0.8871
1.5060	250	-	0.8737
1.8072	300	-	0.8864
2.0	332	-	0.8850
2.1084	350	-	0.8884
2.4096	400	-	0.8776
2.7108	450	-	0.8779
3.0	498	-	0.8864
3.0120	500	1.1103	0.8866
3.3133	550	-	0.8956
3.6145	600	-	0.9069
3.9157	650	-	0.9079
4.0	664	-	0.9055
4.2169	700	-	0.9000
4.5181	750	-	0.8907
4.8193	800	-	0.9033
5.0	830	-	0.9016
5.1205	850	-	0.8950
5.4217	900	-	0.9047
5.7229	950	-	0.9134
6.0	996	-	0.9048
6.0241	1000	0.1809	0.9092
6.3253	1050	-	0.8953
6.6265	1100	-	0.8866
6.9277	1150	-	0.9021
7.0	1162	-	0.9021
7.2289	1200	-	0.9003
7.5301	1250	-	0.8908
7.8313	1300	-	0.8979
8.0	1328	-	0.9024
8.1325	1350	-	0.9008
8.4337	1400	-	0.9061
8.7349	1450	-	0.9125
9.0	1494	-	0.9152
9.0361	1500	0.0889	0.9152
9.3373	1550	-	0.9097
9.6386	1600	-	0.8966
9.9398	1650	-	0.8991
10.0	1660	-	0.9014
10.2410	1700	-	0.9027
10.5422	1750	-	0.9052
10.8434	1800	-	0.8917
11.0	1826	-	0.8936
11.1446	1850	-	0.8941
11.4458	1900	-	0.9058
11.7470	1950	-	0.8983
12.0	1992	-	0.9083
12.0482	2000	0.0658	0.9044
12.3494	2050	-	0.9063
12.6506	2100	-	0.9047
12.9518	2150	-	0.9115
13.0	2158	-	0.9152
13.2530	2200	-	0.9111
13.5542	2250	-	0.9000
13.8554	2300	-	0.9049
14.0	2324	-	0.8991
14.1566	2350	-	0.8891
14.4578	2400	-	0.9017
14.7590	2450	-	0.9050
15.0	2490	-	0.9012
15.0602	2500	0.0517	0.9014
15.3614	2550	-	0.8998
15.6627	2600	-	0.8947
15.9639	2650	-	0.9002
16.0	2656	-	0.8965
16.2651	2700	-	0.9085
16.5663	2750	-	0.8940
16.8675	2800	-	0.8932
17.0	2822	-	0.9066
17.1687	2850	-	0.8960
17.4699	2900	-	0.8908
17.7711	2950	-	0.8991
18.0	2988	-	0.8983
18.0723	3000	0.0569	0.9005
18.3735	3050	-	0.8945
18.6747	3100	-	0.9003
18.9759	3150	-	0.8994
19.0	3154	-	0.9024
19.2771	3200	-	0.9032
19.5783	3250	-	0.8980
19.8795	3300	-	0.8989
20.0	3320	-	0.9020
20.1807	3350	-	0.9023
20.4819	3400	-	0.9033
20.7831	3450	-	0.8907
21.0	3486	-	0.9063
21.0843	3500	0.0318	0.9026
21.3855	3550	-	0.8989
21.6867	3600	-	0.8965
21.9880	3650	-	0.8976
22.0	3652	-	0.8976
22.2892	3700	-	0.8972
22.5904	3750	-	0.9030
22.8916	3800	-	0.8955
23.0	3818	-	0.9011
23.1928	3850	-	0.8968
23.4940	3900	-	0.8970
23.7952	3950	-	0.8978
24.0	3984	-	0.8964
24.0964	4000	0.047	0.8976
24.3976	4050	-	0.9005
24.6988	4100	-	0.9021
25.0	4150	-	0.8991
25.3012	4200	-	0.9021
25.6024	4250	-	0.8944
25.9036	4300	-	0.8984
26.0	4316	-	0.8995
26.2048	4350	-	0.8963
26.5060	4400	-	0.8973
26.8072	4450	-	0.9037
27.0	4482	-	0.9040
27.1084	4500	0.0325	0.8974
27.4096	4550	-	0.8966
27.7108	4600	-	0.8995
28.0	4648	-	0.9012
28.0120	4650	-	0.9012
28.3133	4700	-	0.9068
28.6145	4750	-	0.9069
28.9157	4800	-	0.9072
29.0	4814	-	0.9072
29.2169	4850	-	0.9069
29.5181	4900	-	0.9069
29.8193	4950	-	0.9069
30.0	4980	-	0.9069

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.1
Tokenizers: 0.21.0

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}
}