metadata

base_model: BAAI/bge-base-en-v1.5
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:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      The consolidated financial statements and accompanying notes listed in
      Part IV, Item 15(a)(1) of this Annual Report on Form 10-K are included
      elsewhere in this Annual Report on Form 10-K.
    sentences:
      - >-
        What is the carrying value of the indefinite-lived intangible assets
        related to the Certificate of Needs and Medicare licenses as of December
        31, 2023?
      - >-
        What sections of the Annual Report on Form 10-K contain the company's
        financial statements?
      - >-
        What was the effective tax rate excluding discrete net tax benefits for
        the year 2022?
  - source_sentence: >-
      Consumers are served through Amazon's online and physical stores with an
      emphasis on selection, price, and convenience.
    sentences:
      - >-
        What decision did the European Commission make on July 10, 2023
        regarding the United States?
      - >-
        What are the primary offerings to consumers through Amazon's online and
        physical stores?
      - >-
        What activities are included in the services and other revenue segment
        of General Motors Company?
  - source_sentence: >-
      Visa has traditionally referred to their structure of facilitating secure,
      reliable, and efficient money movement among consumers, issuing and
      acquiring financial institutions, and merchants as the 'four-party' model.
    sentences:
      - >-
        What model does Visa traditionally refer to regarding their transaction
        process among consumers, financial institutions, and merchants?
      - >-
        What percentage of Meta's U.S. workforce in 2023 were represented by
        people with disabilities, veterans, and members of the LGBTQ+ community?
      - >-
        What are the revenue sources for the Company’s Health Care Benefits
        Segment?
  - source_sentence: >-
      In addition to LinkedIn’s free services, LinkedIn offers monetized
      solutions: Talent Solutions, Marketing Solutions, Premium Subscriptions,
      and Sales Solutions. Talent Solutions provide insights for workforce
      planning and tools to hire, nurture, and develop talent. Talent Solutions
      also includes Learning Solutions, which help businesses close critical
      skills gaps in times where companies are having to do more with existing
      talent.
    sentences:
      - >-
        What were the major factors contributing to the increased expenses
        excluding interest for Investor Services and Advisor Services in 2023?
      - >-
        What were the pre-tax earnings of the manufacturing sector in 2023,
        2022, and 2021?
      - What does LinkedIn's Talent Solutions include?
  - source_sentence: >-
      Management assessed the effectiveness of the company’s internal control
      over financial reporting as of December 31, 2023. In making this
      assessment, we used the criteria set forth by the Committee of Sponsoring
      Organizations of the Treadway Commission (COSO) in Internal
      Control—Integrated Framework (2013).
    sentences:
      - >-
        What criteria did Caterpillar Inc. use to assess the effectiveness of
        its internal control over financial reporting as of December 31, 2023?
      - What are the primary components of U.S. sales volumes for Ford?
      - >-
        What was the percentage increase in Schwab's common stock dividend in
        2022?
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.6914285714285714
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8242857142857143
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.86
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9057142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6914285714285714
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2747619047619047
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17199999999999996
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09057142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6914285714285714
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8242857142857143
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.86
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9057142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7996069120234027
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7655430839002263
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7691084355362756
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6857142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8185714285714286
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8657142857142858
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.91
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6857142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27285714285714285
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17314285714285713
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.091
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6857142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8185714285714286
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8657142857142858
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.91
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7977668666030896
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7618548752834466
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7648500519048698
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6885714285714286
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8157142857142857
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8557142857142858
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8957142857142857
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6885714285714286
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27190476190476187
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17114285714285715
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08957142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6885714285714286
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8157142857142857
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8557142857142858
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8957142857142857
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7930130789421053
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7600034013605441
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7638476233890482
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6657142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8057142857142857
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8428571428571429
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8771428571428571
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6657142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26857142857142857
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16857142857142854
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0877142857142857
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6657142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8057142857142857
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8428571428571429
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8771428571428571
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7738190503453819
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.740330498866213
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.744806490732212
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6428571428571429
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7785714285714286
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8142857142857143
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.86
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6428571428571429
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2595238095238095
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16285714285714284
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08599999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6428571428571429
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7785714285714286
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8142857142857143
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.86
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7524157565449978
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.717859977324263
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7225949392448401
            name: Cosine Map@100

BGE base Financial Matryoshka

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

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': 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("amietheace/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Management assessed the effectiveness of the company’s internal control over financial reporting as of December 31, 2023. In making this assessment, we used the criteria set forth by the Committee of Sponsoring Organizations of the Treadway Commission (COSO) in Internal Control—Integrated Framework (2013).',
    'What criteria did Caterpillar Inc. use to assess the effectiveness of its internal control over financial reporting as of December 31, 2023?',
    'What are the primary components of U.S. sales volumes for Ford?',
]
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

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6914
cosine_accuracy@3	0.8243
cosine_accuracy@5	0.86
cosine_accuracy@10	0.9057
cosine_precision@1	0.6914
cosine_precision@3	0.2748
cosine_precision@5	0.172
cosine_precision@10	0.0906
cosine_recall@1	0.6914
cosine_recall@3	0.8243
cosine_recall@5	0.86
cosine_recall@10	0.9057
cosine_ndcg@10	0.7996
cosine_mrr@10	0.7655
cosine_map@100	0.7691

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6857
cosine_accuracy@3	0.8186
cosine_accuracy@5	0.8657
cosine_accuracy@10	0.91
cosine_precision@1	0.6857
cosine_precision@3	0.2729
cosine_precision@5	0.1731
cosine_precision@10	0.091
cosine_recall@1	0.6857
cosine_recall@3	0.8186
cosine_recall@5	0.8657
cosine_recall@10	0.91
cosine_ndcg@10	0.7978
cosine_mrr@10	0.7619
cosine_map@100	0.7649

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6886
cosine_accuracy@3	0.8157
cosine_accuracy@5	0.8557
cosine_accuracy@10	0.8957
cosine_precision@1	0.6886
cosine_precision@3	0.2719
cosine_precision@5	0.1711
cosine_precision@10	0.0896
cosine_recall@1	0.6886
cosine_recall@3	0.8157
cosine_recall@5	0.8557
cosine_recall@10	0.8957
cosine_ndcg@10	0.793
cosine_mrr@10	0.76
cosine_map@100	0.7638

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6657
cosine_accuracy@3	0.8057
cosine_accuracy@5	0.8429
cosine_accuracy@10	0.8771
cosine_precision@1	0.6657
cosine_precision@3	0.2686
cosine_precision@5	0.1686
cosine_precision@10	0.0877
cosine_recall@1	0.6657
cosine_recall@3	0.8057
cosine_recall@5	0.8429
cosine_recall@10	0.8771
cosine_ndcg@10	0.7738
cosine_mrr@10	0.7403
cosine_map@100	0.7448

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6429
cosine_accuracy@3	0.7786
cosine_accuracy@5	0.8143
cosine_accuracy@10	0.86
cosine_precision@1	0.6429
cosine_precision@3	0.2595
cosine_precision@5	0.1629
cosine_precision@10	0.086
cosine_recall@1	0.6429
cosine_recall@3	0.7786
cosine_recall@5	0.8143
cosine_recall@10	0.86
cosine_ndcg@10	0.7524
cosine_mrr@10	0.7179
cosine_map@100	0.7226

Training Details

Training Dataset

json

Dataset: json
Size: 6,300 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 8 tokens
mean: 44.33 tokens
max: 289 tokens

min: 9 tokens
mean: 20.43 tokens
max: 46 tokens

	positive	anchor
type	string	string
details	min: 8 tokens mean: 44.33 tokens max: 289 tokens	min: 9 tokens mean: 20.43 tokens max: 46 tokens

Samples:

positive	anchor
The Company defines fair value as the price received to transfer an asset or paid to transfer a liability in an orderly transaction between market participants at the measurement date. In accordance with ASC 820, Fair Value Measurements and Disclosures, the Company uses the fair value hierarchy which prioritizes the inputs used to measure fair value. The hierarchy gives the highest priority to unadjusted quoted prices in active markets for identical assets or liabilities (Level 1), observable inputs other than quoted prices (Level 2), and unobservable inputs (Level 3).	`What is the role of Level 1, Level 2, and Level 3 inputs in the fair value hierarchy according to ASC 820?`
`In the event of conversion of the Notes, if shares are delivered to the Company under the Capped Call Transactions, they will offset the dilutive effect of the shares that the Company would issue under the Notes.`	`What happens to the dilutive effect of shares issued under the Notes if shares are delivered to the Company under the Capped Call Transactions during the conversion?`
`Marketing expenses increased $48.8 million to $759.2 million in the year ended December 31, 2023 compared to the year ended December 31, 2022.`	`How much did the marketing expenses increase in the year ended December 31, 2023?`

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: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 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: 16
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_768_cosine_map@100	dim_512_cosine_map@100	dim_256_cosine_map@100	dim_128_cosine_map@100	dim_64_cosine_map@100
0.8122	10	1.5603	-	-	-	-	-
0.9746	12	-	0.7538	0.7541	0.7486	0.7280	0.6916
1.6244	20	0.6619	-	-	-	-	-
1.9492	24	-	0.7657	0.7629	0.7583	0.7418	0.7197
2.4365	30	0.4579	-	-	-	-	-
2.9239	36	-	0.7689	0.7643	0.7624	0.7453	0.7240
3.2487	40	0.3997	-	-	-	-	-
3.8985	48	-	0.7691	0.7649	0.7638	0.7448	0.7226

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.0
Transformers: 4.41.2
PyTorch: 2.2.0a0+6a974be
Accelerate: 0.27.0
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}
}