anikulkar's picture
Add new SentenceTransformer model.
d9842b1 verified
metadata
language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
datasets: []
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
widget:
  - source_sentence: >-
      From 2021 to 2022, the operating revenue increased by 4%, from $4,923.9
      million to $5,122.2 million.
    sentences:
      - >-
        How much does the AMC Stubs A-List membership cost per month depending
        on the geographic market?
      - What was the percentage change in operating revenue from 2021 to 2022?
      - >-
        What types of coverage does political risk insurance provide for
        commercial lenders?
  - source_sentence: >-
      Our two operating segments are "Compute & Networking" and "Graphics."
      Refer to Note 17 of the Notes to the Consolidated Financial Statements in
      Part IV, Item 15 of this Annual Report on Form 10-K for additional
      information.
    sentences:
      - >-
        What was the noncash impairment charge recorded in the fourth quarter of
        2023 for the goodwill attributable to FedEx Dataworks?
      - What are the two operating segments of NVIDIA as mentioned in the text?
      - >-
        What is the disclosure threshold for environmental proceedings involving
        monetary sanctions according to SEC regulations?
  - source_sentence: >-
      For 2023, the weighted-average actuarial assumptions for retirement plans
      included a service cost discount rate of 4.85% and a rate of increase in
      compensation levels of 3.71%.
    sentences:
      - >-
        What are the actuarial assumptions for retirement plans discount rate
        and rate of increase in compensation levels in 2023?
      - >-
        Where are accrued interest and penalties related to unrecognized tax
        benefits recorded?
      - >-
        What is the purpose of the Employee Resource Groups (ERGs) in the
        organization?
  - source_sentence: >-
      The Company is currently party to certain legal proceedings, none of which
      we believe to be material to our business or financial condition.
    sentences:
      - >-
        What measures is The Hershey Company taking to ensure sufficient
        liquidity during economic downturns?
      - >-
        What is the impact of structural changes on the unit case volume and
        concentrate sales volume of the company on a consolidated basis or at
        the geographic operating segment level?
      - >-
        What is the company's perspective on the impact of the legal proceedings
        on its financial condition?
  - source_sentence: >-
      We recognize gains and losses on pension and postretirement plan assets
      and obligations immediately in Other income (expense) - net in our
      consolidated statements of income.
    sentences:
      - >-
        Where are gains and losses on pension and postretirement plan assets and
        obligations recognized in financial statements?
      - >-
        What is the total amount of property, plant, and equipment, net,
        reported by the company for the fiscal year 2023?
      - >-
        What were the accumulated benefit obligation and fair value of plan
        assets for certain U.S. pension plans with obligations exceeding assets
        as of December 31, 2023?
pipeline_tag: sentence-similarity
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: 0.6828571428571428
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8228571428571428
            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: 0.6828571428571428
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2742857142857143
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.172
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09057142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6828571428571428
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8228571428571428
            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: 0.7960843632092954
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7607987528344665
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7647429753660495
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6842857142857143
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8228571428571428
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8557142857142858
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9014285714285715
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6842857142857143
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2742857142857143
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17114285714285712
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09014285714285714
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6842857142857143
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8228571428571428
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8557142857142858
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9014285714285715
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7939749538465997
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7593849206349204
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7635559033333911
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.68
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8114285714285714
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.85
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8942857142857142
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.68
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2704761904761905
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08942857142857143
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.68
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8114285714285714
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.85
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8942857142857142
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7888779795440546
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7549767573696146
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7594249239569217
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6571428571428571
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7942857142857143
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8342857142857143
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8885714285714286
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6571428571428571
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26476190476190475
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16685714285714284
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08885714285714284
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6571428571428571
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7942857142857143
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8342857142857143
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8885714285714286
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7729724847261471
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7360578231292516
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.740309728715939
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6185714285714285
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.76
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8657142857142858
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6185714285714285
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2533333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08657142857142855
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6185714285714285
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.76
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8657142857142858
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7409253495656911
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7012964852607709
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7061843304820828
            name: Cosine Map@100

BGE base Financial Matryoshka

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("anikulkar/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'We recognize gains and losses on pension and postretirement plan assets and obligations immediately in Other income (expense) - net in our consolidated statements of income.',
    'Where are gains and losses on pension and postretirement plan assets and obligations recognized in financial statements?',
    'What is the total amount of property, plant, and equipment, net, reported by the company for the fiscal year 2023?',
]
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 0.6829
cosine_accuracy@3 0.8229
cosine_accuracy@5 0.86
cosine_accuracy@10 0.9057
cosine_precision@1 0.6829
cosine_precision@3 0.2743
cosine_precision@5 0.172
cosine_precision@10 0.0906
cosine_recall@1 0.6829
cosine_recall@3 0.8229
cosine_recall@5 0.86
cosine_recall@10 0.9057
cosine_ndcg@10 0.7961
cosine_mrr@10 0.7608
cosine_map@100 0.7647

Information Retrieval

Metric Value
cosine_accuracy@1 0.6843
cosine_accuracy@3 0.8229
cosine_accuracy@5 0.8557
cosine_accuracy@10 0.9014
cosine_precision@1 0.6843
cosine_precision@3 0.2743
cosine_precision@5 0.1711
cosine_precision@10 0.0901
cosine_recall@1 0.6843
cosine_recall@3 0.8229
cosine_recall@5 0.8557
cosine_recall@10 0.9014
cosine_ndcg@10 0.794
cosine_mrr@10 0.7594
cosine_map@100 0.7636

Information Retrieval

Metric Value
cosine_accuracy@1 0.68
cosine_accuracy@3 0.8114
cosine_accuracy@5 0.85
cosine_accuracy@10 0.8943
cosine_precision@1 0.68
cosine_precision@3 0.2705
cosine_precision@5 0.17
cosine_precision@10 0.0894
cosine_recall@1 0.68
cosine_recall@3 0.8114
cosine_recall@5 0.85
cosine_recall@10 0.8943
cosine_ndcg@10 0.7889
cosine_mrr@10 0.755
cosine_map@100 0.7594

Information Retrieval

Metric Value
cosine_accuracy@1 0.6571
cosine_accuracy@3 0.7943
cosine_accuracy@5 0.8343
cosine_accuracy@10 0.8886
cosine_precision@1 0.6571
cosine_precision@3 0.2648
cosine_precision@5 0.1669
cosine_precision@10 0.0889
cosine_recall@1 0.6571
cosine_recall@3 0.7943
cosine_recall@5 0.8343
cosine_recall@10 0.8886
cosine_ndcg@10 0.773
cosine_mrr@10 0.7361
cosine_map@100 0.7403

Information Retrieval

Metric Value
cosine_accuracy@1 0.6186
cosine_accuracy@3 0.76
cosine_accuracy@5 0.8
cosine_accuracy@10 0.8657
cosine_precision@1 0.6186
cosine_precision@3 0.2533
cosine_precision@5 0.16
cosine_precision@10 0.0866
cosine_recall@1 0.6186
cosine_recall@3 0.76
cosine_recall@5 0.8
cosine_recall@10 0.8657
cosine_ndcg@10 0.7409
cosine_mrr@10 0.7013
cosine_map@100 0.7062

Training Details

Training Dataset

Unnamed Dataset

  • 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: 45.24 tokens
    • max: 512 tokens
    • min: 9 tokens
    • mean: 20.71 tokens
    • max: 45 tokens
  • Samples:
    positive anchor
    Changes in Costs. Our costs are subject to fluctuations, particularly due to changes in commodity and input material prices, transportation costs, other broader inflationary impacts and our own productivity efforts. We have significant exposures to certain commodities and input materials, in particular certain oil-derived materials like resins and paper-based materials like pulp. Volatility in the market price of these commodities and input materials has a direct impact on our costs. Disruptions in our manufacturing, supply and distribution operations due to energy shortages, natural disasters, labor or freight constraints have impacted our costs and could do so in the future. New or increased legal or regulatory requirements, along with initiatives to meet our sustainability goals, could also result in increased costs due to higher material costs and investments in facilities and equipment. We strive to implement, achieve and sustain cost improvement plans, including supply chain optimization and general overhead and workforce optimization. Increased pricing in response to certain inflationary or cost increases may also offset portions of the cost impacts; however, such price increases may impact product consumption. If we are unable to manage cost impacts through pricing actions and consistent productivity improvements, it may adversely impact our net sales, gross margin, operating margin, net earnings and cash flows. How did Procter & Gamble manage the fluctuations in costs, particularly related to commodities and input materials?
    As of October 1, 2023 we had ¥5 billion, or $33.5 million, of borrowings outstanding under these credit facilities. How much was borrowed under the Japanese yen-denominated credit facilities as of October 1, 2023?
    AutoZone sells automotive hard parts, maintenance items, accessories and non-automotive products through www.autozone.com, and commercial customers can make purchases through www.autozonepro.com. Additionally, the ALLDATA brand of automotive diagnostic, repair, collision and shop management software is sold through www.alldata.com. What online platforms does AutoZone use for selling automotive products and services?
  • 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: False
  • 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: False
  • 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_128_cosine_map@100 dim_256_cosine_map@100 dim_512_cosine_map@100 dim_64_cosine_map@100 dim_768_cosine_map@100
0.8122 10 1.5647 - - - - -
0.9746 12 - 0.7160 0.7404 0.7515 0.6797 0.7533
1.6244 20 0.6629 - - - - -
1.9492 24 - 0.7340 0.7582 0.7611 0.6996 0.7603
2.4365 30 0.4811 - - - - -
2.9239 36 - 0.7403 0.759 0.7638 0.7056 0.7646
3.2487 40 0.4046 - - - - -
3.8985 48 - 0.7403 0.7594 0.7636 0.7062 0.7647
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.3.0+cu121
  • Accelerate: 0.31.0
  • Datasets: 2.19.2
  • 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}
}