MugheesAwan11's picture
Add new SentenceTransformer model.
d3d8ef0 verified
metadata
base_model: BAAI/bge-base-en-v1.5
datasets: []
language:
  - en
library_name: sentence-transformers
license: apache-2.0
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:882
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      Data Discovery & Classification Sensitive Data Catalog Sensitive Data
      Catalog People Data Graph People Data Graph Data Mapping Automation View
      Data Subject Request Automation View People Data Graph View Assessment
      Automation View Cookie Consent View Universal Consent View Vendor Risk
      Assessment View Breach Management View Privacy Policy Management View
      Privacy Center View Data Security Posture Management View Data Access
      Intelligence & Governance View Data Risk Management View Data Breach
      Analysis View Data Catalog View Data Lineage View Data Quality View Asset
      and Data Discovery View Data Access Intelligence & Governance View Data
      Privacy Automation View
    sentences:
      - >-
        How does coordinating a response in managing a data breach and meeting
        global regulatory obligations help automate compliance with global
        privacy regulations?
      - >-
        What law replaced Law No. 1682/2001 in Paraguay's data protection
        regulations and what are the restrictions on publicizing sensitive data
        under it?
      - >-
        What are the different components or tools related to Data Discovery &
        Classification?
  - source_sentence: >-
      View Assessment Automation View Cookie Consent View Universal Consent View
      Vendor Risk Assessment View Breach Management View Privacy Policy
      Management View Privacy Center View Learn more Security Identify data risk
      and enable protection & control Data Security Posture Management View Data
      Access Intelligence & Governance View Data Risk Management View Data
      Breach Analysis View Learn more Governance Optimize Data Governance with
      granular insights into your data Data Catalog View Data Lineage View Data
      Quality View Data Controls Orchestrator View Solutions Technologies
      Covering you everywhere with 1000+ integrations across data systems.
      Snowflake View AW,  View Assessment Automation View Cookie Consent View
      Universal Consent View Vendor Risk Assessment View Breach Management View
      Privacy Policy Management View Privacy Center View Learn more Security
      Identify data risk and enable protection & control Data Security Posture
      Management View Data Access Intelligence & Governance View Data Risk
      Management View Data Breach Analysis View Learn more Governance Optimize
      Data Governance with granular insights into your data Data Catalog View
      Data Lineage View Data Quality View Data Controls Orchestrator View
      Solutions Technologies Covering you everywhere with 1000+ integrations
      across data systems. Snowflake View AW
    sentences:
      - >-
        What can the data principal do if the data fiduciary disagrees with
        their request for correction, completion, update, or erasure, and how
        does cross-border data transfer factor in?
      - >-
        What is the purpose of the Vendor Risk Assessment for data security and
        governance?
      - >-
        How can privacy automation help in complying with global privacy
        regulations?
  - source_sentence: >-
      of 2021 is the British Virgin Island’s main data protection law on par
      with the EU and UK standards. Learn more ### Jamaica The Data Protection
      Act No. 7 of 2020 is Jamaica’s data protection regulation, enforced by the
      Office of the Information Commissioner. Learn more ### Ukraine The Law on
      Personal Data Protection is Ukraine’s main data protection law, making it
      one of the few such regulations that precede the GDPR in Europe. Learn
      more ### Uzbekistan Uzbekistan has several regulations that govern
      different aspects of data protection within the country. Learn more about
      : Law on Personal Data Bill to Improve the Legal Framework for Personal
      Data Draft Law on Advertising Law on Cybersecurity (No. RK 764) ### Monaco
      Act No. 1.165 on the Protection of Personal Data regulates personal data
      protection-related matters in the Principality of Monaco
    sentences:
      - >-
        What are the conditions for parental consent under PIPL and the
        requirements for privacy notices?
      - >-
        What does the Knowledge Center provide information on in relation to
        security?
      - >-
        Which European country has a data protection law that predates the GDPR
        and is enforced by the Information Commissioner's Office?
  - source_sentence: >-
      Data Lineage View Data Quality View Asset and Data Discovery View Data
      Access Intelligence & Governance View Data Privacy Automation View
      Sensitive Data Intelligence View Data Flow Intelligence & Governance View
      Data Consent Automation View Data Security Posture Management View Data
      Breach Impact Analysis & Response View Data Catalog View Data Lineage View
      Solutions Technologies Regulations Roles Back Snowflake View AWS View
      Microsoft 365 View Salesforce View Workday View GCP View Azure View Oracle
      View US California CCPA View US California CPRA View
    sentences:
      - >-
        What is the role of data privacy automation in ensuring data protection
        and compliance?
      - >-
        What risks does data security and the cloud help control for enterprises
        to safely harness their power?
      - >-
        What is the term for the right to delete personal data upon request,
        also known as 'the right to be forgotten', and what are the other data
        protection rights under GDPR?
  - source_sentence: >-
      Consent of an individual is valid if it is reasonable to expect that an
      individual to whom the organization’s activities are directed would
      understand the nature, purpose, and consequences of the collection, use,
      or disclosure of the personal information to which they are consenting.
      The information must be provided in manageable and easily accessible ways
      to data subjects and data subjects must be allowed to withdraw consent. If
      there is a use or disclosure a data subject would not reasonably expect to
      be occurring, such as certain sharing of information with a third party or
      the tracking of location, express consent would likely be required.
      However, the data subject’s consent may not be required for certain data
      processing activities such as when the collection is “clearly” in the
      interests of the individual and consent cannot be obtained in a timely
      way, data is being collected in the course of employment, journalistic, is
      already publicly available, information is being collected for the
      detection and prevention of fraud or for
    sentences:
      - >-
        How should information be provided to data subjects in manageable and
        easily accessible ways?
      - >-
        What are the obligations and requirements for businesses under China's
        Personal Information Protection Law?
      - >-
        Which state, following California, Virginia, and Colorado, recently
        passed privacy legislation like the VCDPA?
model-index:
  - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.4020618556701031
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5567010309278351
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6804123711340206
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7525773195876289
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4020618556701031
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1855670103092783
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1360824742268041
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07525773195876287
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.4020618556701031
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5567010309278351
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6804123711340206
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7525773195876289
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5649836192344125
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5059687448862709
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5167362215588647
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.3917525773195876
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5876288659793815
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6288659793814433
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7525773195876289
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3917525773195876
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.19587628865979378
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12577319587628866
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07525773195876287
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.3917525773195876
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5876288659793815
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6288659793814433
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7525773195876289
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5625195371806965
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5031173294059894
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5141611082081141
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.38144329896907214
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5773195876288659
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6391752577319587
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.711340206185567
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.38144329896907214
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1924398625429553
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12783505154639174
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07113402061855668
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.38144329896907214
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5773195876288659
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6391752577319587
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.711340206185567
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5460935382949205
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.49311078383243345
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5067772343986099
            name: Cosine Map@100

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) 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): 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("MugheesAwan11/bge-base-securiti-dataset-1-v19")
# Run inference
sentences = [
    'Consent of an individual is valid if it is reasonable to expect that an individual to whom the organization’s activities are directed would understand the nature, purpose, and consequences of the collection, use, or disclosure of the personal information to which they are consenting. The information must be provided in manageable and easily accessible ways to data subjects and data subjects must be allowed to withdraw consent. If there is a use or disclosure a data subject would not reasonably expect to be occurring, such as certain sharing of information with a third party or the tracking of location, express consent would likely be required. However, the data subject’s consent may not be required for certain data processing activities such as when the collection is “clearly” in the interests of the individual and consent cannot be obtained in a timely way, data is being collected in the course of employment, journalistic, is already publicly available, information is being collected for the detection and prevention of fraud or for',
    'How should information be provided to data subjects in manageable and easily accessible ways?',
    'Which state, following California, Virginia, and Colorado, recently passed privacy legislation like the VCDPA?',
]
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

Information Retrieval

Metric Value
cosine_accuracy@1 0.4021
cosine_accuracy@3 0.5567
cosine_accuracy@5 0.6804
cosine_accuracy@10 0.7526
cosine_precision@1 0.4021
cosine_precision@3 0.1856
cosine_precision@5 0.1361
cosine_precision@10 0.0753
cosine_recall@1 0.4021
cosine_recall@3 0.5567
cosine_recall@5 0.6804
cosine_recall@10 0.7526
cosine_ndcg@10 0.565
cosine_mrr@10 0.506
cosine_map@100 0.5167

Information Retrieval

Metric Value
cosine_accuracy@1 0.3918
cosine_accuracy@3 0.5876
cosine_accuracy@5 0.6289
cosine_accuracy@10 0.7526
cosine_precision@1 0.3918
cosine_precision@3 0.1959
cosine_precision@5 0.1258
cosine_precision@10 0.0753
cosine_recall@1 0.3918
cosine_recall@3 0.5876
cosine_recall@5 0.6289
cosine_recall@10 0.7526
cosine_ndcg@10 0.5625
cosine_mrr@10 0.5031
cosine_map@100 0.5142

Information Retrieval

Metric Value
cosine_accuracy@1 0.3814
cosine_accuracy@3 0.5773
cosine_accuracy@5 0.6392
cosine_accuracy@10 0.7113
cosine_precision@1 0.3814
cosine_precision@3 0.1924
cosine_precision@5 0.1278
cosine_precision@10 0.0711
cosine_recall@1 0.3814
cosine_recall@3 0.5773
cosine_recall@5 0.6392
cosine_recall@10 0.7113
cosine_ndcg@10 0.5461
cosine_mrr@10 0.4931
cosine_map@100 0.5068

Training Details

Training Dataset

Unnamed Dataset

  • Size: 882 training samples
  • Columns: positive and anchor
  • Approximate statistics based on the first 1000 samples:
    positive anchor
    type string string
    details
    • min: 18 tokens
    • mean: 227.32 tokens
    • max: 414 tokens
    • min: 10 tokens
    • mean: 21.98 tokens
    • max: 102 tokens
  • Samples:
    positive anchor
    Leader in Data Privacy View Events Spotlight Talks Education Contact Us Schedule a Demo Products By Use Cases By Roles Data Command Center View Learn more Asset and Data Discovery Discover dark and native data assets Learn more Data Access Intelligence & Governance Identify which users have access to sensitive data and prevent unauthorized access Learn more Data Privacy Automation PrivacyCenter.Cloud Data Mapping
    data subject must be notified of any such extension within one month of receiving the request, along with the reasons for the delay and the possibility of complaining to the supervisory authority. The right to restrict processing applies when the data subject contests data accuracy, the processing is unlawful, and the data subject opposes erasure and requests restriction. The controller must inform data subjects before any such restriction is lifted. Under GDPR, the data subject also has the right to obtain from the controller the rectification of inaccurate personal data and to have incomplete personal data completed. Article: 22 Under PDPL, if a decision is based solely on automated processing of personal data intended to assess the data subject regarding his/her performance at work, financial standing, credit-worthiness, reliability, or conduct, then the data subject has the right to request processing in a manner that is not solely automated. This right shall not apply where the decision is taken in the course of entering into What is the requirement for notifying the data subject of any extension under GDPR and PDPL?
    Automation PrivacyCenter.Cloud Data Mapping
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            768,
            512,
            256
        ],
        "matryoshka_weights": [
            1,
            1,
            1
        ],
        "n_dims_per_step": -1
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: epoch
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 16
  • learning_rate: 2e-05
  • num_train_epochs: 4
  • lr_scheduler_type: cosine
  • warmup_ratio: 0.1
  • bf16: True
  • tf32: True
  • load_best_model_at_end: True
  • optim: adamw_torch_fused
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: epoch
  • prediction_loss_only: True
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 16
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • learning_rate: 2e-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: 4
  • max_steps: -1
  • lr_scheduler_type: cosine
  • 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
  • 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: True
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: True
  • 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: True
  • 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_fused
  • 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_eval_metrics: False
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss dim_256_cosine_map@100 dim_512_cosine_map@100 dim_768_cosine_map@100
0.3571 10 4.0517 - - -
0.7143 20 2.5778 - - -
1.0 28 - 0.5304 0.5224 0.5234
1.0714 30 2.1161 - - -
1.4286 40 1.5394 - - -
1.7857 50 1.5162 - - -
2.0 56 - 0.5412 0.5382 0.5185
2.1429 60 1.202 - - -
2.5 70 1.0456 - - -
2.8571 80 1.1341 - - -
3.0 84 - 0.5340 0.5554 0.5498
3.2143 90 0.8724 - - -
3.5714 100 0.932 - - -
3.9286 110 0.9548 - - -
4.0 112 - 0.5296 0.5487 0.5491
0.3571 10 0.9958 - - -
0.7143 20 0.8264 - - -
1.0 28 - 0.5155 0.5250 0.5269
1.0714 30 0.7969 - - -
1.4286 40 0.6244 - - -
1.7857 50 0.6368 - - -
2.0 56 - 0.5034 0.5314 0.5233
2.1429 60 0.4748 - - -
2.5 70 0.4037 - - -
2.8571 80 0.4615 - - -
3.0 84 - 0.5079 0.5145 0.5155
3.2143 90 0.3148 - - -
3.5714 100 0.4142 - - -
3.9286 110 0.366 - - -
4.0 112 - 0.5068 0.5142 0.5167
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.1.2+cu121
  • Accelerate: 0.31.0
  • Datasets: 2.19.1
  • 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}
}